@cursor/july 0.1.108 → 0.1.111
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/AGENTS.md +3 -7
- package/README.md +3 -21
- package/dist/bin/agent-serve.js +81 -66
- package/dist/channels/bitbucket/api.d.ts +41 -0
- package/dist/channels/bitbucket/api.d.ts.map +1 -1
- package/dist/channels/bitbucket/api.js +266 -6
- package/dist/channels/bitbucket/binding.d.ts +4 -0
- package/dist/channels/bitbucket/binding.d.ts.map +1 -1
- package/dist/channels/bitbucket/binding.js +20 -4
- package/dist/channels/bitbucket/bitbucket-channel.js +1 -1
- package/dist/channels/bitbucket/bitbucket-webhook.js +1 -1
- package/dist/channels/bitbucket/checks.d.ts.map +1 -1
- package/dist/channels/bitbucket/checks.js +1 -1
- package/dist/channels/bitbucket/cursor-account.js +1 -1
- package/dist/channels/bitbucket/events.js +1 -1
- package/dist/channels/bitbucket/index.d.ts +1 -1
- package/dist/channels/bitbucket/index.d.ts.map +1 -1
- package/dist/channels/bitbucket/index.js +1 -1
- package/dist/channels/change-monitors/change-monitors-channel.js +1 -1
- package/dist/channels/checks.d.ts.map +1 -1
- package/dist/channels/checks.js +2 -2
- package/dist/channels/deployments/deployments-channel.js +1 -1
- package/dist/channels/github/cursor-account.js +3 -3
- package/dist/channels/github/defaults.d.ts.map +1 -1
- package/dist/channels/github/defaults.js +5 -3
- package/dist/channels/github/events.js +1 -1
- package/dist/channels/github/forward.js +8 -8
- package/dist/channels/github/github-channel.d.ts.map +1 -1
- package/dist/channels/github/github-channel.js +17 -13
- package/dist/channels/github/progress.d.ts.map +1 -1
- package/dist/channels/github/progress.js +7 -2
- package/dist/channels/github/state.d.ts +6 -0
- package/dist/channels/github/state.d.ts.map +1 -1
- package/dist/channels/github/types.d.ts +6 -0
- package/dist/channels/github/types.d.ts.map +1 -1
- package/dist/channels/gitlab/api.d.ts +27 -0
- package/dist/channels/gitlab/api.d.ts.map +1 -1
- package/dist/channels/gitlab/api.js +88 -0
- package/dist/channels/gitlab/binding.d.ts +5 -0
- package/dist/channels/gitlab/binding.d.ts.map +1 -1
- package/dist/channels/gitlab/binding.js +14 -4
- package/dist/channels/gitlab/checks.d.ts.map +1 -1
- package/dist/channels/gitlab/checks.js +1 -1
- package/dist/channels/gitlab/cursor-account.js +1 -1
- package/dist/channels/gitlab/events.js +1 -1
- package/dist/channels/gitlab/gitlab-channel.js +1 -1
- package/dist/channels/gitlab/gitlab-webhook.js +1 -1
- package/dist/channels/gitlab/index.d.ts +1 -1
- package/dist/channels/gitlab/index.d.ts.map +1 -1
- package/dist/channels/gitlab/index.js +1 -1
- package/dist/channels/gitlab/replay.js +2 -2
- package/dist/channels/origin/binding.d.ts +2 -0
- package/dist/channels/origin/binding.d.ts.map +1 -1
- package/dist/channels/origin/binding.js +3 -3
- package/dist/channels/origin/checks.d.ts +19 -7
- package/dist/channels/origin/checks.d.ts.map +1 -1
- package/dist/channels/origin/checks.js +13 -9
- package/dist/channels/origin/cursor-account.js +1 -1
- package/dist/channels/origin/defaults.d.ts.map +1 -1
- package/dist/channels/origin/defaults.js +3 -1
- package/dist/channels/origin/events.js +1 -1
- package/dist/channels/origin/origin-channel.d.ts.map +1 -1
- package/dist/channels/origin/origin-channel.js +2 -1
- package/dist/channels/origin/origin-webhook.js +2 -2
- package/dist/channels/slack/agentic-delivery.d.ts +23 -0
- package/dist/channels/slack/agentic-delivery.d.ts.map +1 -0
- package/dist/channels/slack/agentic-delivery.js +558 -0
- package/dist/channels/slack/agentic-posted.d.ts +30 -0
- package/dist/channels/slack/agentic-posted.d.ts.map +1 -0
- package/dist/channels/slack/agentic-posted.js +102 -0
- package/dist/channels/slack/agentic-signals.d.ts +48 -0
- package/dist/channels/slack/agentic-signals.d.ts.map +1 -0
- package/dist/channels/slack/agentic-signals.js +204 -0
- package/dist/channels/slack/api.d.ts +20 -1
- package/dist/channels/slack/api.d.ts.map +1 -1
- package/dist/channels/slack/api.js +43 -11
- package/dist/channels/slack/approvals.js +1 -1
- package/dist/channels/slack/auth.d.ts.map +1 -1
- package/dist/channels/slack/auth.js +3 -1
- package/dist/channels/slack/blocks.js +3 -3
- package/dist/channels/slack/bot-mentions.d.ts.map +1 -1
- package/dist/channels/slack/bot-mentions.js +5 -5
- package/dist/channels/slack/channel-watch.js +1 -1
- package/dist/channels/slack/cli-project.js +3 -3
- package/dist/channels/slack/defaults.d.ts +3 -0
- package/dist/channels/slack/defaults.d.ts.map +1 -1
- package/dist/channels/slack/defaults.js +90 -29
- package/dist/channels/slack/dispatch.d.ts +44 -1
- package/dist/channels/slack/dispatch.d.ts.map +1 -1
- package/dist/channels/slack/dispatch.js +233 -103
- package/dist/channels/slack/doctor.js +1 -1
- package/dist/channels/slack/eval-directive.js +1 -1
- package/dist/channels/slack/external-policy.d.ts +2 -1
- package/dist/channels/slack/external-policy.d.ts.map +1 -1
- package/dist/channels/slack/external-policy.js +13 -2
- package/dist/channels/slack/footer.d.ts +30 -0
- package/dist/channels/slack/footer.d.ts.map +1 -0
- package/dist/channels/slack/footer.js +88 -0
- package/dist/channels/slack/index.d.ts +2 -0
- package/dist/channels/slack/index.d.ts.map +1 -1
- package/dist/channels/slack/index.js +2 -0
- package/dist/channels/slack/interactive.d.ts.map +1 -1
- package/dist/channels/slack/interactive.js +5 -3
- package/dist/channels/slack/live-delivery.d.ts +1 -1
- package/dist/channels/slack/live-delivery.d.ts.map +1 -1
- package/dist/channels/slack/live-delivery.js +20 -6
- package/dist/channels/slack/log.d.ts.map +1 -1
- package/dist/channels/slack/log.js +1 -1
- package/dist/channels/slack/manifest.js +1 -1
- package/dist/channels/slack/nudge-carrier.js +1 -1
- package/dist/channels/slack/nudge-store.js +2 -2
- package/dist/channels/slack/paint-start.d.ts +22 -0
- package/dist/channels/slack/paint-start.d.ts.map +1 -0
- package/dist/channels/slack/paint-start.js +91 -0
- package/dist/channels/slack/placeholder.d.ts +36 -0
- package/dist/channels/slack/placeholder.d.ts.map +1 -0
- package/dist/channels/slack/placeholder.js +240 -0
- package/dist/channels/slack/progress-delivery.d.ts.map +1 -1
- package/dist/channels/slack/progress-delivery.js +13 -4
- package/dist/channels/slack/reasoning-chip.d.ts +8 -0
- package/dist/channels/slack/reasoning-chip.d.ts.map +1 -0
- package/dist/channels/slack/reasoning-chip.js +30 -0
- package/dist/channels/slack/recording-sink.d.ts +29 -0
- package/dist/channels/slack/recording-sink.d.ts.map +1 -0
- package/dist/channels/slack/recording-sink.js +142 -0
- package/dist/channels/slack/reply-options.d.ts +8 -1
- package/dist/channels/slack/reply-options.d.ts.map +1 -1
- package/dist/channels/slack/reply-options.js +59 -14
- package/dist/channels/slack/setup.js +1 -1
- package/dist/channels/slack/slack-channel.d.ts +12 -5
- package/dist/channels/slack/slack-channel.d.ts.map +1 -1
- package/dist/channels/slack/slack-channel.js +110 -24
- package/dist/channels/slack/socket-mode.js +2 -2
- package/dist/channels/slack/thread-context.js +5 -5
- package/dist/channels/slack/tool-approval-events.d.ts +5 -0
- package/dist/channels/slack/tool-approval-events.d.ts.map +1 -1
- package/dist/channels/slack/tool-approval-events.js +50 -38
- package/dist/channels/slack/tool-cards.js +1 -1
- package/dist/channels/slack/tool-chip.d.ts +9 -0
- package/dist/channels/slack/tool-chip.d.ts.map +1 -0
- package/dist/channels/slack/tool-chip.js +25 -0
- package/dist/channels/slack/types.d.ts +49 -7
- package/dist/channels/slack/types.d.ts.map +1 -1
- package/dist/channels/slack/upload.d.ts +13 -0
- package/dist/channels/slack/upload.d.ts.map +1 -0
- package/dist/channels/slack/upload.js +135 -0
- package/dist/channels.d.ts +10 -14
- package/dist/channels.d.ts.map +1 -1
- package/dist/channels.js +9 -21
- package/dist/dashboard-session-url.d.ts +15 -0
- package/dist/dashboard-session-url.d.ts.map +1 -0
- package/dist/dashboard-session-url.js +25 -0
- package/dist/docs/404.html +3 -3
- package/dist/docs/architecture.svg +59 -0
- package/dist/docs/assets/app.Drol6mi6.js +309 -0
- package/dist/docs/assets/{building-with-agents.md.CUSWxlP_.js → building-with-agents.md.CEGVXkmO.js} +2 -2
- package/dist/docs/assets/{building-with-agents.md.CUSWxlP_.lean.js → building-with-agents.md.CEGVXkmO.lean.js} +1 -1
- package/dist/docs/assets/chunks/@localSearchIndexroot.DtXk1hy-.js +1 -0
- package/dist/docs/assets/chunks/{VPLocalSearchBox.BOKxlYGP.js → VPLocalSearchBox.CdqoBZJX.js} +2 -2
- package/dist/docs/assets/chunks/arc.BVX3ycTn.js +1 -0
- package/dist/docs/assets/chunks/architectureDiagram-Q4EWVU46.CcChnMxX.js +36 -0
- package/dist/docs/assets/chunks/baseUniq.xwtXO-yt.js +1 -0
- package/dist/docs/assets/chunks/blockDiagram-DXYQGD6D.CijZ_taK.js +132 -0
- package/dist/docs/assets/chunks/c4Diagram-AHTNJAMY.0FBvwBvK.js +10 -0
- package/dist/docs/assets/chunks/channel.Bkv1N-gK.js +1 -0
- package/dist/docs/assets/chunks/chunk-4BX2VUAB.CELMmMDA.js +1 -0
- package/dist/docs/assets/chunks/chunk-4TB4RGXK.C4bhFtSm.js +206 -0
- package/dist/docs/assets/chunks/chunk-55IACEB6.ZnQ9gRRQ.js +1 -0
- package/dist/docs/assets/chunks/chunk-EDXVE4YY.DPlmglG-.js +1 -0
- package/dist/docs/assets/chunks/chunk-FMBD7UC4.BrUk8pff.js +15 -0
- package/dist/docs/assets/chunks/chunk-OYMX7WX6.CcmWIncu.js +231 -0
- package/dist/docs/assets/chunks/chunk-QZHKN3VN.D65-cs8I.js +1 -0
- package/dist/docs/assets/chunks/chunk-YZCP3GAM.qoXZpG9F.js +1 -0
- package/dist/docs/assets/chunks/classDiagram-6PBFFD2Q.CZDco1o8.js +1 -0
- package/dist/docs/assets/chunks/classDiagram-v2-HSJHXN6E.CZDco1o8.js +1 -0
- package/dist/docs/assets/chunks/clone.YSt_40_s.js +1 -0
- package/dist/docs/assets/chunks/cose-bilkent-S5V4N54A.8rYtqudO.js +1 -0
- package/dist/docs/assets/chunks/cytoscape.esm.BQk4lpUV.js +331 -0
- package/dist/docs/assets/chunks/dagre-KV5264BT.DrRP1fOh.js +4 -0
- package/dist/docs/assets/chunks/defaultLocale.C4B-KCzX.js +1 -0
- package/dist/docs/assets/chunks/diagram-5BDNPKRD.DHj_xA2_.js +10 -0
- package/dist/docs/assets/chunks/diagram-G4DWMVQ6.Bz_6nAKj.js +24 -0
- package/dist/docs/assets/chunks/diagram-MMDJMWI5.BWA0xSW9.js +43 -0
- package/dist/docs/assets/chunks/diagram-TYMM5635.CpTJLNJI.js +24 -0
- package/dist/docs/assets/chunks/erDiagram-SMLLAGMA.-7AWWSrP.js +85 -0
- package/dist/docs/assets/chunks/flowDiagram-DWJPFMVM.BTnQ742_.js +162 -0
- package/dist/docs/assets/chunks/framework.dypDpWZ3.js +19 -0
- package/dist/docs/assets/chunks/ganttDiagram-T4ZO3ILL.B5_HiiQ5.js +292 -0
- package/dist/docs/assets/chunks/gitGraphDiagram-UUTBAWPF.CZcNTFZd.js +106 -0
- package/dist/docs/assets/chunks/graph.V2GLaab4.js +1 -0
- package/dist/docs/assets/chunks/infoDiagram-42DDH7IO.7pZOkCCU.js +2 -0
- package/dist/docs/assets/chunks/init.Gi6I4Gst.js +1 -0
- package/dist/docs/assets/chunks/ishikawaDiagram-UXIWVN3A.DSMo3Qa3.js +70 -0
- package/dist/docs/assets/chunks/journeyDiagram-VCZTEJTY.BNEgWN1S.js +139 -0
- package/dist/docs/assets/chunks/kanban-definition-6JOO6SKY.B-4d4tC7.js +89 -0
- package/dist/docs/assets/chunks/katex.DkKDou_j.js +257 -0
- package/dist/docs/assets/chunks/layout.Dvbn9nSb.js +1 -0
- package/dist/docs/assets/chunks/linear.D2GM4p4b.js +1 -0
- package/dist/docs/assets/chunks/min.DVBtLK-B.js +1 -0
- package/dist/docs/assets/chunks/mindmap-definition-QFDTVHPH.CnJRI55x.js +96 -0
- package/dist/docs/assets/chunks/ordinal.DBvzRdQf.js +1 -0
- package/dist/docs/assets/chunks/pieDiagram-DEJITSTG.CtoaTFlA.js +30 -0
- package/dist/docs/assets/chunks/quadrantDiagram-34T5L4WZ.DtT24_vN.js +7 -0
- package/dist/docs/assets/chunks/requirementDiagram-MS252O5E.CjSO4o8f.js +84 -0
- package/dist/docs/assets/chunks/sankeyDiagram-XADWPNL6.-wWiIVWa.js +10 -0
- package/dist/docs/assets/chunks/sequenceDiagram-FGHM5R23.DSk8s4gX.js +157 -0
- package/dist/docs/assets/chunks/stateDiagram-FHFEXIEX.BFKAsdkN.js +1 -0
- package/dist/docs/assets/chunks/stateDiagram-v2-QKLJ7IA2.C4CLm481.js +1 -0
- package/dist/docs/assets/chunks/{theme.DbDZW-zb.js → theme.C0MctGaz.js} +2 -2
- package/dist/docs/assets/chunks/timeline-definition-GMOUNBTQ.TUNJbAFe.js +120 -0
- package/dist/docs/assets/chunks/vennDiagram-DHZGUBPP.C-RGNnk4.js +34 -0
- package/dist/docs/assets/chunks/virtual_mermaid-config.DDnGl6nM.js +1 -0
- package/dist/docs/assets/chunks/wardley-RL74JXVD.g5efOWmT.js +162 -0
- package/dist/docs/assets/chunks/wardleyDiagram-NUSXRM2D.DH4zt73Y.js +20 -0
- package/dist/docs/assets/chunks/xychartDiagram-5P7HB3ND.B-3k6bF6.js +7 -0
- package/dist/docs/assets/{deployment.md.JenwuCCB.js → deployment.md.Dm4Qo3hp.js} +5 -5
- package/dist/docs/assets/{deployment.md.JenwuCCB.lean.js → deployment.md.Dm4Qo3hp.lean.js} +1 -1
- package/dist/docs/assets/evals.md.BLDRt5LH.js +211 -0
- package/dist/docs/assets/evals.md.BLDRt5LH.lean.js +1 -0
- package/dist/docs/assets/guides_agent-to-agent.md.BI0xclmy.js +14 -0
- package/dist/docs/assets/guides_agent-to-agent.md.BI0xclmy.lean.js +1 -0
- package/dist/docs/assets/guides_bitbucket.md.CTpCl__f.js +10 -0
- package/dist/docs/assets/guides_bitbucket.md.CTpCl__f.lean.js +1 -0
- package/dist/docs/assets/{guides_cloud-agents.md.BsloyHdY.js → guides_cloud-agents.md.lSE_l7lH.js} +2 -2
- package/dist/docs/assets/{guides_cloud-agents.md.BsloyHdY.lean.js → guides_cloud-agents.md.lSE_l7lH.lean.js} +1 -1
- package/dist/docs/assets/{guides_convert-automation.md.B4sjlodG.js → guides_convert-automation.md.Ck6Cr68A.js} +1 -1
- package/dist/docs/assets/{guides_convert-automation.md.B4sjlodG.lean.js → guides_convert-automation.md.Ck6Cr68A.lean.js} +1 -1
- package/dist/docs/assets/{guides_github.md.BH33UEBJ.js → guides_github.md.D6ER29dG.js} +13 -3
- package/dist/docs/assets/{guides_github.md.BH33UEBJ.lean.js → guides_github.md.D6ER29dG.lean.js} +1 -1
- package/dist/docs/assets/guides_gitlab.md.P-TjBnS5.js +14 -0
- package/dist/docs/assets/guides_gitlab.md.P-TjBnS5.lean.js +1 -0
- package/dist/docs/assets/guides_grokbot-agents.md.WBZIOvkz.js +9 -0
- package/dist/docs/assets/{guides_grokbot-agents.md.DyV-WArv.lean.js → guides_grokbot-agents.md.WBZIOvkz.lean.js} +1 -1
- package/dist/docs/assets/{guides_improve.md.BGVk32bK.js → guides_improve.md.BKaDuKKK.js} +1 -1
- package/dist/docs/assets/{guides_improve.md.BGVk32bK.lean.js → guides_improve.md.BKaDuKKK.lean.js} +1 -1
- package/dist/docs/assets/{guides_mcp-oauth.md.Dp6cDP7f.js → guides_mcp-oauth.md.DMNMpXtO.js} +1 -1
- package/dist/docs/assets/{guides_mcp-oauth.md.Dp6cDP7f.lean.js → guides_mcp-oauth.md.DMNMpXtO.lean.js} +1 -1
- package/dist/docs/assets/{guides_opentelemetry.md.SCRMskno.js → guides_opentelemetry.md._CRfDyzH.js} +14 -14
- package/dist/docs/assets/{guides_opentelemetry.md.SCRMskno.lean.js → guides_opentelemetry.md._CRfDyzH.lean.js} +1 -1
- package/dist/docs/assets/{guides_slack.md.D4RVMM4G.js → guides_slack.md.DdT8rmsj.js} +12 -4
- package/dist/docs/assets/{guides_slack.md.D4RVMM4G.lean.js → guides_slack.md.DdT8rmsj.lean.js} +1 -1
- package/dist/docs/assets/{guides_webhooks.md.DKdA43Qm.js → guides_webhooks.md.aQW10HRe.js} +3 -3
- package/dist/docs/assets/{guides_webhooks.md.DKdA43Qm.lean.js → guides_webhooks.md.aQW10HRe.lean.js} +1 -1
- package/dist/docs/assets/hillclimbing.md.Dq4kkVIL.js +1 -0
- package/dist/docs/assets/hillclimbing.md.Dq4kkVIL.lean.js +1 -0
- package/dist/docs/assets/index.md.BFVyY2KT.js +17 -0
- package/dist/docs/assets/index.md.BFVyY2KT.lean.js +1 -0
- package/dist/docs/assets/{quickstart.md.DdQOF7Y8.js → quickstart.md.D3MjSZN-.js} +30 -38
- package/dist/docs/assets/quickstart.md.D3MjSZN-.lean.js +1 -0
- package/dist/docs/assets/{reference_agent-config.md.CvoL6pof.js → reference_agent-config.md.CfVA-LZJ.js} +1 -1
- package/dist/docs/assets/{reference_agent-config.md.CvoL6pof.lean.js → reference_agent-config.md.CfVA-LZJ.lean.js} +1 -1
- package/dist/docs/assets/{reference_artifacts.md.Dior32Qw.js → reference_artifacts.md.Vf7qyIZ-.js} +1 -1
- package/dist/docs/assets/{reference_artifacts.md.Dior32Qw.lean.js → reference_artifacts.md.Vf7qyIZ-.lean.js} +1 -1
- package/dist/docs/assets/{reference_channels.md.D-qTqwcq.js → reference_channels.md.icqLKcTc.js} +2 -12
- package/dist/docs/assets/{reference_channels.md.D-qTqwcq.lean.js → reference_channels.md.icqLKcTc.lean.js} +1 -1
- package/dist/docs/assets/{reference_cli.md.Ca26u0Es.js → reference_cli.md.B2dBL6L8.js} +4 -4
- package/dist/docs/assets/{reference_cli.md.Ca26u0Es.lean.js → reference_cli.md.B2dBL6L8.lean.js} +1 -1
- package/dist/docs/assets/{reference_connections.md.BojkC6c5.js → reference_connections.md.Cb3U_c8n.js} +4 -4
- package/dist/docs/assets/{reference_connections.md.BojkC6c5.lean.js → reference_connections.md.Cb3U_c8n.lean.js} +1 -1
- package/dist/docs/assets/{reference_extensions.md.CPWt00ds.js → reference_extensions.md.wlFD3cUR.js} +3 -3
- package/dist/docs/assets/{reference_extensions.md.CPWt00ds.lean.js → reference_extensions.md.wlFD3cUR.lean.js} +1 -1
- package/dist/docs/assets/{reference_hooks.md.Ddt5DdgJ.js → reference_hooks.md.CZuynAxj.js} +3 -3
- package/dist/docs/assets/{reference_hooks.md.Ddt5DdgJ.lean.js → reference_hooks.md.CZuynAxj.lean.js} +1 -1
- package/dist/docs/assets/{reference_http-api.md.oySXBO8o.js → reference_http-api.md.DTKcYE6L.js} +3 -3
- package/dist/docs/assets/{reference_http-api.md.oySXBO8o.lean.js → reference_http-api.md.DTKcYE6L.lean.js} +1 -1
- package/dist/docs/assets/{reference_instructions.md.CR7XSsGk.js → reference_instructions.md.D7gkckK-.js} +1 -1
- package/dist/docs/assets/{reference_instructions.md.CR7XSsGk.lean.js → reference_instructions.md.D7gkckK-.lean.js} +1 -1
- package/dist/docs/assets/{reference_playground.md.4myJPxrf.js → reference_playground.md.D2YExv5K.js} +1 -1
- package/dist/docs/assets/{reference_playground.md.4myJPxrf.lean.js → reference_playground.md.D2YExv5K.lean.js} +1 -1
- package/dist/docs/assets/reference_project-layout.md.DPxbUJyt.js +19 -0
- package/dist/docs/assets/{reference_project-layout.md.DuBu9a96.lean.js → reference_project-layout.md.DPxbUJyt.lean.js} +1 -1
- package/dist/docs/assets/{reference_prompt.md.DnaD5dNK.js → reference_prompt.md.BQ5uAv1F.js} +1 -1
- package/dist/docs/assets/{reference_prompt.md.DnaD5dNK.lean.js → reference_prompt.md.BQ5uAv1F.lean.js} +1 -1
- package/dist/docs/assets/{reference_schedules.md.DI_JrHgq.js → reference_schedules.md.BasfZWO-.js} +1 -1
- package/dist/docs/assets/{reference_schedules.md.DI_JrHgq.lean.js → reference_schedules.md.BasfZWO-.lean.js} +1 -1
- package/dist/docs/assets/reference_sessions.md.YKvIsWAx.js +1 -0
- package/dist/docs/assets/{reference_sessions.md.CueyOHSL.lean.js → reference_sessions.md.YKvIsWAx.lean.js} +1 -1
- package/dist/docs/assets/{reference_skills.md.l2ezAcaN.js → reference_skills.md.rNgpsGd0.js} +1 -1
- package/dist/docs/assets/{reference_skills.md.l2ezAcaN.lean.js → reference_skills.md.rNgpsGd0.lean.js} +1 -1
- package/dist/docs/assets/{reference_subagents.md.CfsIloPm.js → reference_subagents.md.e5qitjJt.js} +2 -2
- package/dist/docs/assets/{reference_subagents.md.CfsIloPm.lean.js → reference_subagents.md.e5qitjJt.lean.js} +1 -1
- package/dist/docs/assets/{reference_tools.md.aGrn99hP.js → reference_tools.md.BdCO2aHZ.js} +4 -4
- package/dist/docs/assets/{reference_tools.md.aGrn99hP.lean.js → reference_tools.md.BdCO2aHZ.lean.js} +1 -1
- package/dist/docs/assets/{style.DCD_zyg3.css → style.Cfo2vbik.css} +1 -1
- package/dist/docs/assets/{templates_agentic-owners.md.BZSH4N9z.js → templates_agentic-owners.md.Da_AGDlH.js} +1 -1
- package/dist/docs/assets/{templates_agentic-owners.md.BZSH4N9z.lean.js → templates_agentic-owners.md.Da_AGDlH.lean.js} +1 -1
- package/dist/docs/assets/{templates_pr-autofixer.md.Bds_XWcV.js → templates_pr-autofixer.md.DqxocIGh.js} +1 -1
- package/dist/docs/assets/{templates_pr-autofixer.md.Bds_XWcV.lean.js → templates_pr-autofixer.md.DqxocIGh.lean.js} +1 -1
- package/dist/docs/assets/{templates_security-reviewer.md.lshxbCLK.js → templates_security-reviewer.md.Bhnvd8VE.js} +1 -1
- package/dist/docs/assets/{templates_security-reviewer.md.lshxbCLK.lean.js → templates_security-reviewer.md.Bhnvd8VE.lean.js} +1 -1
- package/dist/docs/assets/{templates_triage.md.Co4UNzkZ.js → templates_triage.md.BdBWO9Ic.js} +1 -1
- package/dist/docs/assets/{templates_triage.md.Co4UNzkZ.lean.js → templates_triage.md.BdBWO9Ic.lean.js} +1 -1
- package/dist/docs/assets/{troubleshooting.md.CYEAO9bM.js → troubleshooting.md.BcgNoYtJ.js} +1 -1
- package/dist/docs/assets/{troubleshooting.md.CYEAO9bM.lean.js → troubleshooting.md.BcgNoYtJ.lean.js} +1 -1
- package/dist/docs/building-with-agents.html +41 -8
- package/dist/docs/building-with-agents.md +15 -16
- package/dist/docs/deployment.html +44 -11
- package/dist/docs/deployment.md +6 -7
- package/dist/docs/evals.html +196 -37
- package/dist/docs/evals.md +612 -297
- package/dist/docs/guides/agent-to-agent.html +48 -11
- package/dist/docs/guides/agent-to-agent.md +40 -83
- package/dist/docs/guides/bitbucket.html +69 -0
- package/dist/docs/guides/bitbucket.md +84 -0
- package/dist/docs/guides/cloud-agents.html +41 -8
- package/dist/docs/guides/cloud-agents.md +24 -20
- package/dist/docs/guides/convert-automation.html +41 -8
- package/dist/docs/guides/github.html +52 -9
- package/dist/docs/guides/github.md +32 -1
- package/dist/docs/guides/gitlab.html +73 -0
- package/dist/docs/guides/gitlab.md +92 -0
- package/dist/docs/guides/grokbot-agents.html +41 -8
- package/dist/docs/guides/grokbot-agents.md +26 -19
- package/dist/docs/guides/improve.html +41 -8
- package/dist/docs/guides/mcp-oauth.html +41 -8
- package/dist/docs/guides/mcp-oauth.md +1 -1
- package/dist/docs/guides/opentelemetry.html +53 -20
- package/dist/docs/guides/opentelemetry.md +28 -41
- package/dist/docs/guides/slack.html +51 -10
- package/dist/docs/guides/slack.md +53 -4
- package/dist/docs/guides/webhooks.html +42 -9
- package/dist/docs/guides/webhooks.md +7 -6
- package/dist/docs/hashmap.json +1 -1
- package/dist/docs/hillclimbing.html +40 -10
- package/dist/docs/hillclimbing.md +7 -7
- package/dist/docs/index.html +57 -12
- package/dist/docs/index.md +81 -146
- package/dist/docs/llms-full.txt +1368 -5551
- package/dist/docs/llms.txt +6 -31
- package/dist/docs/quickstart.html +70 -45
- package/dist/docs/quickstart.md +44 -105
- package/dist/docs/reference/agent-config.html +41 -8
- package/dist/docs/reference/artifacts.html +41 -8
- package/dist/docs/reference/channels.html +41 -18
- package/dist/docs/reference/channels.md +16 -19
- package/dist/docs/reference/cli.html +43 -10
- package/dist/docs/reference/cli.md +6 -20
- package/dist/docs/reference/connections.html +43 -10
- package/dist/docs/reference/connections.md +3 -5
- package/dist/docs/reference/extensions.html +43 -10
- package/dist/docs/reference/extensions.md +2 -5
- package/dist/docs/reference/hooks.html +42 -9
- package/dist/docs/reference/hooks.md +11 -16
- package/dist/docs/reference/http-api.html +42 -9
- package/dist/docs/reference/http-api.md +6 -7
- package/dist/docs/reference/instructions.html +41 -8
- package/dist/docs/reference/playground.html +40 -7
- package/dist/docs/reference/playground.md +2 -6
- package/dist/docs/reference/project-layout.html +42 -9
- package/dist/docs/reference/project-layout.md +4 -12
- package/dist/docs/reference/prompt.html +41 -8
- package/dist/docs/reference/schedules.html +41 -8
- package/dist/docs/reference/sessions.html +40 -7
- package/dist/docs/reference/sessions.md +6 -6
- package/dist/docs/reference/skills.html +41 -8
- package/dist/docs/reference/subagents.html +41 -8
- package/dist/docs/reference/subagents.md +2 -4
- package/dist/docs/reference/tools.html +43 -10
- package/dist/docs/reference/tools.md +2 -5
- package/dist/docs/templates/agentic-owners.html +41 -8
- package/dist/docs/templates/pr-autofixer.html +41 -8
- package/dist/docs/templates/security-reviewer.html +41 -8
- package/dist/docs/templates/triage.html +41 -8
- package/dist/docs/troubleshooting.html +40 -7
- package/dist/docs/troubleshooting.md +1 -2
- package/dist/evals/assertions.js +19 -19
- package/dist/evals/expect.js +1 -1
- package/dist/evals/judge.js +1 -1
- package/dist/evals/reporters.d.ts.map +1 -1
- package/dist/evals/reporters.js +8 -8
- package/dist/evals/run-facts.js +2 -2
- package/dist/evals.d.ts +1 -1
- package/dist/evals.d.ts.map +1 -1
- package/dist/evals.js +7 -7
- package/dist/extensions/cursor-cloud-agents/extension.js +1 -1
- package/dist/extensions/cursor-cloud-agents/lib/backend.js +3 -3
- package/dist/extensions/cursor-cloud-agents/lib/fleet.js +1 -1
- package/dist/extensions/cursor-cloud-agents/lib/repos.js +6 -6
- package/dist/extensions/cursor-cloud-agents/lib/transcript.d.ts.map +1 -1
- package/dist/extensions/cursor-cloud-agents/lib/transcript.js +2 -2
- package/dist/extensions/cursor-cloud-agents/tools/list.js +1 -1
- package/dist/extensions/improve/skills/yourself.js +1 -1
- package/dist/extensions/slack-communication/extension.d.ts +28 -0
- package/dist/extensions/slack-communication/extension.d.ts.map +1 -0
- package/dist/extensions/slack-communication/extension.js +32 -0
- package/dist/extensions/slack-communication/skills/slack-voice.d.ts +5 -0
- package/dist/extensions/slack-communication/skills/slack-voice.d.ts.map +1 -0
- package/dist/extensions/slack-communication/skills/slack-voice.js +54 -0
- package/dist/extensions/slack-communication/tools/delete-message.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/delete-message.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/delete-message.js +29 -0
- package/dist/extensions/slack-communication/tools/edit-message.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/edit-message.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/edit-message.js +37 -0
- package/dist/extensions/slack-communication/tools/post-card.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/post-card.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/post-card.js +25 -0
- package/dist/extensions/slack-communication/tools/post-file.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/post-file.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/post-file.js +76 -0
- package/dist/extensions/slack-communication/tools/post-update.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/post-update.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/post-update.js +36 -0
- package/dist/extensions/slack-communication/tools/react.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/react.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/react.js +27 -0
- package/dist/extensions/slack-communication/tools/set-status.d.ts +4 -0
- package/dist/extensions/slack-communication/tools/set-status.d.ts.map +1 -0
- package/dist/extensions/slack-communication/tools/set-status.js +18 -0
- package/dist/extensions.d.ts +2 -3
- package/dist/extensions.d.ts.map +1 -1
- package/dist/extensions.js +2 -5
- package/dist/files-backends/cursor-hosted.d.ts +18 -6
- package/dist/files-backends/cursor-hosted.d.ts.map +1 -1
- package/dist/files-backends/cursor-hosted.js +357 -74
- package/dist/files-backends/local-fs.js +1 -1
- package/dist/files.d.ts +15 -0
- package/dist/files.d.ts.map +1 -1
- package/dist/filesystem.d.ts.map +1 -1
- package/dist/filesystem.js +15 -15
- package/dist/index.d.ts +6 -10
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +5 -8
- package/dist/internal/advertise-tools.js +6 -6
- package/dist/internal/approval-gate.js +1 -1
- package/dist/internal/artifacts-store.js +3 -3
- package/dist/internal/as-of.js +2 -2
- package/dist/internal/authored-alias-hooks.d.ts +5 -0
- package/dist/internal/authored-alias-hooks.d.ts.map +1 -1
- package/dist/internal/authored-alias-hooks.js +17 -0
- package/dist/internal/authored-loaders.d.ts +4 -0
- package/dist/internal/authored-loaders.d.ts.map +1 -1
- package/dist/internal/authored-loaders.js +21 -2
- package/dist/internal/builtin-tools/reminders.js +2 -2
- package/dist/internal/chat-client.js +5 -5
- package/dist/internal/cli-ax.d.ts +2 -2
- package/dist/internal/cli-ax.d.ts.map +1 -1
- package/dist/internal/cli-ax.js +69 -15
- package/dist/internal/cli-bitbucket.js +10 -10
- package/dist/internal/cli-convert-automation.js +2 -2
- package/dist/internal/cli-cursor.d.ts +3 -11
- package/dist/internal/cli-cursor.d.ts.map +1 -1
- package/dist/internal/cli-cursor.js +5 -10
- package/dist/internal/cli-deploy.d.ts +12 -2
- package/dist/internal/cli-deploy.d.ts.map +1 -1
- package/dist/internal/cli-deploy.js +328 -96
- package/dist/internal/cli-docs.js +5 -5
- package/dist/internal/cli-github.js +15 -16
- package/dist/internal/cli-gitlab.js +10 -10
- package/dist/internal/cli-manifest.js +1 -1
- package/dist/internal/cli-mcp-oauth.d.ts.map +1 -1
- package/dist/internal/cli-mcp-oauth.js +5 -5
- package/dist/internal/cli-mcp.js +3 -3
- package/dist/internal/cli-skills.js +2 -2
- package/dist/internal/cli-slack.js +5 -5
- package/dist/internal/cloud-turn-cost.js +1 -1
- package/dist/internal/continuation-channel.d.ts.map +1 -1
- package/dist/internal/continuation-channel.js +2 -2
- package/dist/internal/continuation-identity.d.ts.map +1 -1
- package/dist/internal/continuation-identity.js +22 -12
- package/dist/internal/conversation-mirror.d.ts.map +1 -1
- package/dist/internal/conversation-mirror.js +33 -2
- package/dist/internal/convert-automation/convert-workflow.js +25 -24
- package/dist/internal/convert-automation/types.d.ts +8 -0
- package/dist/internal/convert-automation/types.d.ts.map +1 -1
- package/dist/internal/cursor/account-mcp.d.ts +2 -2
- package/dist/internal/cursor/account-mcp.d.ts.map +1 -1
- package/dist/internal/cursor/account-mcp.js +32 -27
- package/dist/internal/cursor/backend-client.d.ts +15 -10
- package/dist/internal/cursor/backend-client.d.ts.map +1 -1
- package/dist/internal/cursor/backend-client.js +17 -11
- package/dist/internal/cursor/credentials.js +1 -1
- package/dist/internal/cursor/hosted-store-secrets.d.ts +16 -0
- package/dist/internal/cursor/hosted-store-secrets.d.ts.map +1 -1
- package/dist/internal/cursor/hosted-store-secrets.js +25 -0
- package/dist/internal/cursor-account-mcp-auth.js +9 -9
- package/dist/internal/cursor-deployment-relay.js +9 -9
- package/dist/internal/cursor-event-relay.js +10 -10
- package/dist/internal/cursor-relay-core.js +2 -2
- package/dist/internal/deploy-client.d.ts +106 -9
- package/dist/internal/deploy-client.d.ts.map +1 -1
- package/dist/internal/deploy-client.js +171 -23
- package/dist/internal/deploy-manifest.d.ts +13 -0
- package/dist/internal/deploy-manifest.d.ts.map +1 -1
- package/dist/internal/deploy-manifest.js +32 -16
- package/dist/internal/discovery/agent-config.d.ts +5 -0
- package/dist/internal/discovery/agent-config.d.ts.map +1 -1
- package/dist/internal/discovery/agent-config.js +27 -0
- package/dist/internal/discovery/agent.d.ts +1 -1
- package/dist/internal/discovery/agent.d.ts.map +1 -1
- package/dist/internal/discovery/agent.js +10 -13
- package/dist/internal/discovery/channels.js +4 -4
- package/dist/internal/discovery/connections.js +4 -4
- package/dist/internal/discovery/cursor-plugin.js +12 -12
- package/dist/internal/discovery/extension-overlay.d.ts +1 -2
- package/dist/internal/discovery/extension-overlay.d.ts.map +1 -1
- package/dist/internal/discovery/extension-overlay.js +3 -17
- package/dist/internal/discovery/extensions.d.ts +1 -2
- package/dist/internal/discovery/extensions.d.ts.map +1 -1
- package/dist/internal/discovery/extensions.js +10 -28
- package/dist/internal/discovery/info.d.ts.map +1 -1
- package/dist/internal/discovery/info.js +44 -26
- package/dist/internal/discovery/instructions.js +1 -1
- package/dist/internal/discovery/modules.js +0 -1
- package/dist/internal/discovery/project.d.ts.map +1 -1
- package/dist/internal/discovery/project.js +4 -20
- package/dist/internal/discovery/services.js +1 -1
- package/dist/internal/discovery/tools.js +1 -1
- package/dist/internal/docs-site.js +2 -2
- package/dist/internal/env-file.js +1 -1
- package/dist/internal/eval-run-store.d.ts.map +1 -1
- package/dist/internal/eval-run-store.js +7 -7
- package/dist/internal/eval-runner.js +14 -15
- package/dist/internal/evals-client.js +4 -4
- package/dist/internal/event-log.js +8 -8
- package/dist/internal/event-mapper.d.ts +18 -0
- package/dist/internal/event-mapper.d.ts.map +1 -1
- package/dist/internal/event-mapper.js +34 -2
- package/dist/internal/filesystem/format.d.ts.map +1 -1
- package/dist/internal/filesystem/format.js +6 -3
- package/dist/internal/filesystem/scratch.js +3 -3
- package/dist/internal/filesystem/tools.d.ts.map +1 -1
- package/dist/internal/filesystem/tools.js +6 -6
- package/dist/internal/filesystem/walk.js +1 -1
- package/dist/internal/framework-file-storage.d.ts +10 -7
- package/dist/internal/framework-file-storage.d.ts.map +1 -1
- package/dist/internal/framework-file-storage.js +95 -7
- package/dist/internal/framework-storage-selection.d.ts +2 -8
- package/dist/internal/framework-storage-selection.d.ts.map +1 -1
- package/dist/internal/framework-storage-selection.js +4 -13
- package/dist/internal/github-fanout.js +3 -3
- package/dist/internal/guest-network.js +4 -4
- package/dist/internal/host-files.js +1 -1
- package/dist/internal/host-kv.js +2 -2
- package/dist/internal/hosted-admission-adapter.d.ts +2 -0
- package/dist/internal/hosted-admission-adapter.d.ts.map +1 -1
- package/dist/internal/hosted-catch-protocol.d.ts.map +1 -1
- package/dist/internal/hosted-catch-protocol.js +2 -4
- package/dist/internal/hosted-catch.js +1 -1
- package/dist/internal/hosted-delivery-protocol.d.ts +29 -0
- package/dist/internal/hosted-delivery-protocol.d.ts.map +1 -1
- package/dist/internal/hosted-delivery-protocol.js +76 -8
- package/dist/internal/hosted-delivery.d.ts.map +1 -1
- package/dist/internal/hosted-delivery.js +201 -64
- package/dist/internal/hosted-execution-diag.js +3 -3
- package/dist/internal/hosted-execution-latency.d.ts +80 -0
- package/dist/internal/hosted-execution-latency.d.ts.map +1 -0
- package/dist/internal/hosted-execution-latency.js +220 -0
- package/dist/internal/hosting.d.ts +5 -5
- package/dist/internal/hosting.d.ts.map +1 -1
- package/dist/internal/hosting.js +5 -6
- package/dist/internal/http-channel-define.d.ts +11 -0
- package/dist/internal/http-channel-define.d.ts.map +1 -0
- package/dist/internal/http-channel-define.js +18 -0
- package/dist/internal/http-channel.d.ts +2 -3
- package/dist/internal/http-channel.d.ts.map +1 -1
- package/dist/internal/http-channel.js +3 -4
- package/dist/internal/http-control-plane-session.d.ts +7 -3
- package/dist/internal/http-control-plane-session.d.ts.map +1 -1
- package/dist/internal/http-control-plane-session.js +22 -10
- package/dist/internal/incoming-headers-to-fetch.d.ts +10 -0
- package/dist/internal/incoming-headers-to-fetch.d.ts.map +1 -0
- package/dist/internal/incoming-headers-to-fetch.js +41 -0
- package/dist/internal/init-interview.js +7 -7
- package/dist/internal/init-project.d.ts.map +1 -1
- package/dist/internal/init-project.js +14 -14
- package/dist/internal/init-scaffold.d.ts.map +1 -1
- package/dist/internal/init-scaffold.js +2 -3
- package/dist/internal/inline-stdio-mcp.js +2 -2
- package/dist/internal/install-cursor-skills.d.ts +5 -2
- package/dist/internal/install-cursor-skills.d.ts.map +1 -1
- package/dist/internal/install-cursor-skills.js +35 -15
- package/dist/internal/json-schema.js +1 -1
- package/dist/internal/local-control-plane.d.ts.map +1 -1
- package/dist/internal/local-control-plane.js +3 -3
- package/dist/internal/local-env.js +3 -3
- package/dist/internal/log-ring.js +1 -1
- package/dist/internal/logs-client.js +1 -1
- package/dist/internal/mcp-endpoint.js +8 -8
- package/dist/internal/mcp-host.js +4 -4
- package/dist/internal/mcp-oauth-on-demand.js +3 -3
- package/dist/internal/mcp-oauth.js +5 -5
- package/dist/internal/net.js +2 -2
- package/dist/internal/otel/config.js +3 -3
- package/dist/internal/otel/runtime.js +13 -13
- package/dist/internal/peer-connections.js +2 -2
- package/dist/internal/platform-schedule-sync.js +1 -1
- package/dist/internal/platform-timers.js +1 -1
- package/dist/internal/playground/static.js +2 -2
- package/dist/internal/playground/toolchain.js +2 -2
- package/dist/internal/playground-proxy.js +3 -3
- package/dist/internal/process-memory-telemetry.js +1 -1
- package/dist/internal/reminder-runner.d.ts.map +1 -1
- package/dist/internal/reminder-runner.js +7 -7
- package/dist/internal/reminder-store.js +1 -1
- package/dist/internal/request-error-status.d.ts.map +1 -1
- package/dist/internal/request-error-status.js +9 -0
- package/dist/internal/resolved-connections.js +8 -8
- package/dist/internal/result-output.d.ts +14 -2
- package/dist/internal/result-output.d.ts.map +1 -1
- package/dist/internal/result-output.js +45 -2
- package/dist/internal/router.js +4 -4
- package/dist/internal/run-client.d.ts +1 -1
- package/dist/internal/run-client.js +2 -2
- package/dist/internal/schedule-runner.js +6 -6
- package/dist/internal/scm/pr-url.d.ts +3 -1
- package/dist/internal/scm/pr-url.d.ts.map +1 -1
- package/dist/internal/scm/pr-url.js +10 -2
- package/dist/internal/sdk-runner.d.ts.map +1 -1
- package/dist/internal/sdk-runner.js +15 -16
- package/dist/internal/serve-restart.js +1 -1
- package/dist/internal/server.d.ts.map +1 -1
- package/dist/internal/server.js +81 -101
- package/dist/internal/session-cost.js +3 -3
- package/dist/internal/session-engine.d.ts +39 -35
- package/dist/internal/session-engine.d.ts.map +1 -1
- package/dist/internal/session-engine.js +394 -343
- package/dist/internal/session-run-log.d.ts.map +1 -1
- package/dist/internal/session-run-log.js +4 -4
- package/dist/internal/session-store.d.ts +47 -3
- package/dist/internal/session-store.d.ts.map +1 -1
- package/dist/internal/session-store.js +198 -33
- package/dist/internal/sessions-client.js +3 -3
- package/dist/internal/slack-thread-key.d.ts +7 -0
- package/dist/internal/slack-thread-key.d.ts.map +1 -0
- package/dist/internal/slack-thread-key.js +10 -0
- package/dist/internal/sleep.js +1 -1
- package/dist/internal/storage-coordinator.d.ts +22 -19
- package/dist/internal/storage-coordinator.d.ts.map +1 -1
- package/dist/internal/storage-coordinator.js +114 -73
- package/dist/internal/storage-roles.d.ts +4 -9
- package/dist/internal/storage-roles.d.ts.map +1 -1
- package/dist/internal/storage-roles.js +2 -2
- package/dist/internal/storage.d.ts +2 -0
- package/dist/internal/storage.d.ts.map +1 -0
- package/dist/internal/storage.js +1 -0
- package/dist/internal/store-mirror.js +4 -4
- package/dist/internal/terminal-style.js +2 -2
- package/dist/internal/tool-result.js +3 -3
- package/dist/internal/trajectory.js +7 -7
- package/dist/internal/turn-governor.js +2 -2
- package/dist/internal/turn-outbox.js +1 -1
- package/dist/internal/update-check.js +2 -2
- package/dist/internal/v2-hosting.d.ts +9 -0
- package/dist/internal/v2-hosting.d.ts.map +1 -1
- package/dist/internal/v2-hosting.js +10 -0
- package/dist/internal/workspace.d.ts +13 -10
- package/dist/internal/workspace.d.ts.map +1 -1
- package/dist/internal/workspace.js +17 -16
- package/dist/kv/memory-kv.d.ts +6 -4
- package/dist/kv/memory-kv.d.ts.map +1 -1
- package/dist/kv/memory-kv.js +9 -7
- package/dist/kv.d.ts +4 -7
- package/dist/kv.d.ts.map +1 -1
- package/dist/kv.js +4 -7
- package/dist/otel-public.d.ts +7 -0
- package/dist/otel-public.d.ts.map +1 -0
- package/dist/otel-public.js +5 -0
- package/dist/otel.d.ts +7 -2
- package/dist/otel.d.ts.map +1 -1
- package/dist/otel.js +7 -2
- package/dist/playground/assets/index-BLlKgZtI.css +1 -0
- package/dist/playground/assets/index-CDS5p9sR.js +67 -0
- package/dist/playground/index.html +2 -2
- package/dist/prompt.js +1 -1
- package/dist/result.d.ts +10 -4
- package/dist/result.d.ts.map +1 -1
- package/dist/result.js +9 -3
- package/dist/storage-backends/cursor-hosted-v2.d.ts +4 -5
- package/dist/storage-backends/cursor-hosted-v2.d.ts.map +1 -1
- package/dist/storage-backends/cursor-hosted-v2.js +6 -7
- package/dist/storage-backends/cursor-hosted.d.ts +6 -19
- package/dist/storage-backends/cursor-hosted.d.ts.map +1 -1
- package/dist/storage-backends/cursor-hosted.js +6 -50
- package/dist/storage-backends/file-kv.d.ts +9 -12
- package/dist/storage-backends/file-kv.d.ts.map +1 -1
- package/dist/storage-backends/file-kv.js +18 -54
- package/dist/storage-protocol.d.ts +3 -11
- package/dist/storage-protocol.d.ts.map +1 -1
- package/dist/storage-protocol.js +3 -11
- package/dist/storage.d.ts +28 -38
- package/dist/storage.d.ts.map +1 -1
- package/dist/storage.js +15 -50
- package/dist/types.d.ts +87 -68
- package/dist/types.d.ts.map +1 -1
- package/dist/types.js +12 -4
- package/docs/README.md +83 -148
- package/docs/building-with-agents.md +15 -16
- package/docs/deployment.md +6 -7
- package/docs/evals.md +613 -298
- package/docs/guides/agent-to-agent.md +41 -84
- package/docs/guides/bitbucket.md +89 -0
- package/docs/guides/cloud-agents.md +25 -20
- package/docs/guides/github.md +32 -1
- package/docs/guides/gitlab.md +97 -0
- package/docs/guides/grokbot-agents.md +27 -19
- package/docs/guides/mcp-oauth.md +1 -1
- package/docs/guides/opentelemetry.md +28 -41
- package/docs/guides/slack.md +53 -4
- package/docs/guides/webhooks.md +7 -6
- package/docs/hillclimbing.md +7 -7
- package/docs/quickstart.md +45 -106
- package/docs/reference/channels.md +16 -19
- package/docs/reference/cli.md +6 -20
- package/docs/reference/connections.md +3 -5
- package/docs/reference/extensions.md +2 -5
- package/docs/reference/hooks.md +11 -16
- package/docs/reference/http-api.md +6 -7
- package/docs/reference/playground.md +2 -6
- package/docs/reference/project-layout.md +4 -12
- package/docs/reference/sessions.md +6 -6
- package/docs/reference/subagents.md +2 -4
- package/docs/reference/tools.md +2 -5
- package/docs/troubleshooting.md +1 -2
- package/package.json +55 -43
- package/skills/deploy/SKILL.md +169 -0
- package/skills/evals/SKILL.md +45 -8
- package/skills/framework-map/SKILL.md +3 -4
- package/skills/otel/SKILL.md +8 -18
- package/src/bin/agent-serve.ts +93 -72
- package/src/channels/bitbucket/api.ts +347 -6
- package/src/channels/bitbucket/binding.ts +29 -4
- package/src/channels/bitbucket/bitbucket-channel.ts +1 -1
- package/src/channels/bitbucket/bitbucket-webhook.ts +1 -1
- package/src/channels/bitbucket/checks.ts +3 -4
- package/src/channels/bitbucket/cursor-account.ts +1 -1
- package/src/channels/bitbucket/events.ts +1 -1
- package/src/channels/bitbucket/index.ts +2 -0
- package/src/channels/change-monitors/change-monitors-channel.ts +2 -2
- package/src/channels/checks.ts +5 -4
- package/src/channels/deployments/deployments-channel.ts +1 -1
- package/src/channels/github/api.ts +1 -1
- package/src/channels/github/checks.ts +1 -1
- package/src/channels/github/cursor-account.ts +3 -3
- package/src/channels/github/defaults.ts +8 -4
- package/src/channels/github/events.ts +1 -1
- package/src/channels/github/forward.ts +8 -8
- package/src/channels/github/github-channel.ts +19 -2
- package/src/channels/github/progress.ts +7 -2
- package/src/channels/github/state.ts +6 -0
- package/src/channels/github/types.ts +6 -0
- package/src/channels/gitlab/api.ts +123 -0
- package/src/channels/gitlab/binding.ts +16 -4
- package/src/channels/gitlab/checks.ts +3 -4
- package/src/channels/gitlab/cursor-account.ts +1 -1
- package/src/channels/gitlab/events.ts +1 -1
- package/src/channels/gitlab/gitlab-channel.ts +1 -1
- package/src/channels/gitlab/gitlab-webhook.ts +1 -1
- package/src/channels/gitlab/index.ts +1 -0
- package/src/channels/gitlab/replay.ts +2 -2
- package/src/channels/origin/binding.ts +6 -3
- package/src/channels/origin/checks.ts +27 -17
- package/src/channels/origin/cursor-account.ts +1 -1
- package/src/channels/origin/defaults.ts +5 -1
- package/src/channels/origin/events.ts +1 -1
- package/src/channels/origin/origin-channel.ts +2 -1
- package/src/channels/origin/origin-webhook.ts +2 -2
- package/src/channels/slack/agentic-delivery.ts +659 -0
- package/src/channels/slack/agentic-posted.ts +148 -0
- package/src/channels/slack/agentic-signals.ts +248 -0
- package/src/channels/slack/api.ts +51 -11
- package/src/channels/slack/approvals.ts +1 -1
- package/src/channels/slack/attachments.ts +1 -1
- package/src/channels/slack/auth.ts +3 -1
- package/src/channels/slack/blocks.ts +3 -3
- package/src/channels/slack/bot-mentions.ts +5 -7
- package/src/channels/slack/channel-watch.ts +1 -1
- package/src/channels/slack/cli-project.ts +3 -3
- package/src/channels/slack/defaults.ts +109 -37
- package/src/channels/slack/dispatch.ts +323 -164
- package/src/channels/slack/doctor.ts +1 -1
- package/src/channels/slack/eval-directive.ts +1 -1
- package/src/channels/slack/external-policy.ts +15 -2
- package/src/channels/slack/footer.ts +108 -0
- package/src/channels/slack/index.ts +2 -0
- package/src/channels/slack/interactive.ts +4 -2
- package/src/channels/slack/live-delivery.ts +23 -7
- package/src/channels/slack/log.ts +1 -1
- package/src/channels/slack/manifest.ts +1 -1
- package/src/channels/slack/nudge-carrier.ts +1 -1
- package/src/channels/slack/nudge-store.ts +2 -2
- package/src/channels/slack/paint-start.ts +93 -0
- package/src/channels/slack/placeholder.ts +315 -0
- package/src/channels/slack/progress-delivery.ts +14 -1
- package/src/channels/slack/reasoning-chip.ts +48 -0
- package/src/channels/slack/recording-sink.ts +176 -0
- package/src/channels/slack/reply-options.ts +71 -15
- package/src/channels/slack/setup.ts +1 -1
- package/src/channels/slack/slack-channel.ts +140 -18
- package/src/channels/slack/socket-mode.ts +2 -2
- package/src/channels/slack/thread-context.ts +5 -5
- package/src/channels/slack/tool-approval-events.ts +54 -38
- package/src/channels/slack/tool-cards.ts +1 -1
- package/src/channels/slack/tool-chip.ts +36 -0
- package/src/channels/slack/types.ts +47 -7
- package/src/channels/slack/upload.ts +142 -0
- package/src/channels.ts +12 -30
- package/src/dashboard-session-url.ts +32 -0
- package/src/evals/assertions.ts +19 -19
- package/src/evals/expect.ts +1 -1
- package/src/evals/judge.ts +1 -1
- package/src/evals/reporters.ts +8 -9
- package/src/evals/run-facts.ts +2 -2
- package/src/evals.ts +7 -10
- package/src/extensions/cursor-cloud-agents/extension.ts +1 -1
- package/src/extensions/cursor-cloud-agents/lib/backend.ts +3 -3
- package/src/extensions/cursor-cloud-agents/lib/fleet.ts +1 -1
- package/src/extensions/cursor-cloud-agents/lib/repos.ts +3 -3
- package/src/extensions/cursor-cloud-agents/lib/transcript.ts +3 -4
- package/src/extensions/cursor-cloud-agents/tools/list.ts +1 -1
- package/src/extensions/improve/skills/yourself.ts +1 -1
- package/src/extensions/slack-communication/evals/harness.ts +728 -0
- package/src/extensions/slack-communication/evals/slack-communication.eval.ts +953 -0
- package/src/extensions/slack-communication/evals/slack-placeholder.eval.ts +194 -0
- package/src/extensions/slack-communication/extension.ts +45 -0
- package/src/extensions/slack-communication/skills/slack-voice.ts +59 -0
- package/src/extensions/slack-communication/tools/delete-message.ts +34 -0
- package/src/extensions/slack-communication/tools/edit-message.ts +42 -0
- package/src/extensions/slack-communication/tools/post-card.ts +28 -0
- package/src/extensions/slack-communication/tools/post-file.ts +85 -0
- package/src/extensions/slack-communication/tools/post-update.ts +41 -0
- package/src/extensions/slack-communication/tools/react.ts +33 -0
- package/src/extensions/slack-communication/tools/set-status.ts +21 -0
- package/src/extensions.ts +2 -6
- package/src/files-backends/cursor-hosted.ts +502 -98
- package/src/files-backends/local-fs.ts +1 -1
- package/src/files.ts +15 -0
- package/src/filesystem.ts +16 -18
- package/src/index.ts +4 -39
- package/src/internal/advertise-tools.ts +6 -6
- package/src/internal/approval-gate.ts +1 -1
- package/src/internal/artifacts-store.ts +3 -3
- package/src/internal/as-of.ts +2 -2
- package/src/internal/authored-alias-hooks.ts +32 -0
- package/src/internal/authored-loaders.ts +25 -2
- package/src/internal/builtin-tools/reminders.ts +2 -2
- package/src/internal/chat-client.ts +5 -5
- package/src/internal/cli-ax.ts +85 -16
- package/src/internal/cli-bitbucket.ts +11 -11
- package/src/internal/cli-convert-automation.ts +2 -2
- package/src/internal/cli-cursor.ts +5 -16
- package/src/internal/cli-deploy.ts +389 -104
- package/src/internal/cli-docs.ts +5 -5
- package/src/internal/cli-github.ts +16 -19
- package/src/internal/cli-gitlab.ts +11 -11
- package/src/internal/cli-manifest.ts +1 -1
- package/src/internal/cli-mcp-oauth.ts +5 -7
- package/src/internal/cli-mcp.ts +3 -3
- package/src/internal/cli-skills.ts +2 -2
- package/src/internal/cli-slack.ts +5 -5
- package/src/internal/cloud-turn-cost.ts +1 -1
- package/src/internal/continuation-channel.ts +2 -1
- package/src/internal/continuation-identity.ts +23 -11
- package/src/internal/conversation-mirror.ts +36 -3
- package/src/internal/convert-automation/convert-workflow.ts +27 -27
- package/src/internal/convert-automation/types.ts +9 -0
- package/src/internal/cursor/account-mcp.ts +48 -31
- package/src/internal/cursor/backend-client.ts +28 -17
- package/src/internal/cursor/credentials.ts +1 -1
- package/src/internal/cursor/hosted-store-secrets.ts +34 -0
- package/src/internal/cursor-account-mcp-auth.ts +9 -9
- package/src/internal/cursor-deployment-relay.ts +10 -10
- package/src/internal/cursor-event-relay.ts +10 -10
- package/src/internal/cursor-relay-core.ts +2 -2
- package/src/internal/deploy-client.ts +266 -24
- package/src/internal/deploy-manifest.ts +46 -8
- package/src/internal/discovery/agent-config.ts +34 -0
- package/src/internal/discovery/agent.ts +15 -13
- package/src/internal/discovery/channels.ts +4 -4
- package/src/internal/discovery/connections.ts +4 -4
- package/src/internal/discovery/cursor-plugin.ts +12 -12
- package/src/internal/discovery/extension-overlay.ts +3 -21
- package/src/internal/discovery/extensions.ts +8 -32
- package/src/internal/discovery/info.ts +12 -22
- package/src/internal/discovery/instructions.ts +1 -1
- package/src/internal/discovery/modules.ts +0 -1
- package/src/internal/discovery/project.ts +4 -20
- package/src/internal/discovery/services.ts +1 -1
- package/src/internal/discovery/tools.ts +1 -1
- package/src/internal/docs-site.ts +2 -2
- package/src/internal/env-file.ts +2 -2
- package/src/internal/eval-run-store.ts +7 -9
- package/src/internal/eval-runner.ts +20 -21
- package/src/internal/evals-client.ts +6 -6
- package/src/internal/event-log.ts +10 -10
- package/src/internal/event-mapper.ts +37 -2
- package/src/internal/filesystem/format.ts +11 -12
- package/src/internal/filesystem/scratch.ts +3 -3
- package/src/internal/filesystem/tools.ts +6 -8
- package/src/internal/filesystem/walk.ts +1 -1
- package/src/internal/framework-file-storage.ts +108 -9
- package/src/internal/framework-storage-selection.ts +4 -14
- package/src/internal/github-fanout.ts +4 -4
- package/src/internal/guest-network.ts +4 -4
- package/src/internal/host-files.ts +1 -1
- package/src/internal/host-kv.ts +2 -2
- package/src/internal/hosted-admission-adapter.ts +2 -0
- package/src/internal/hosted-catch-protocol.ts +3 -5
- package/src/internal/hosted-catch.ts +1 -1
- package/src/internal/hosted-delivery-protocol.ts +111 -13
- package/src/internal/hosted-delivery.ts +286 -81
- package/src/internal/hosted-execution-diag.ts +3 -3
- package/src/internal/hosted-execution-latency.ts +334 -0
- package/src/internal/hosting.ts +5 -6
- package/src/internal/http-channel-define.ts +27 -0
- package/src/internal/http-channel.ts +3 -4
- package/src/internal/http-control-plane-session.ts +24 -11
- package/src/internal/incoming-headers-to-fetch.ts +54 -0
- package/src/internal/init-interview.ts +7 -7
- package/src/internal/init-project.ts +14 -16
- package/src/internal/init-scaffold.ts +2 -3
- package/src/internal/inline-stdio-mcp.ts +2 -2
- package/src/internal/install-cursor-skills.ts +49 -16
- package/src/internal/json-schema.ts +1 -1
- package/src/internal/local-control-plane.ts +4 -5
- package/src/internal/local-env.ts +3 -3
- package/src/internal/log-ring.ts +1 -1
- package/src/internal/logs-client.ts +1 -1
- package/src/internal/mcp-endpoint.ts +10 -10
- package/src/internal/mcp-host.ts +9 -9
- package/src/internal/mcp-oauth-on-demand.ts +3 -3
- package/src/internal/mcp-oauth.ts +5 -5
- package/src/internal/net.ts +2 -2
- package/src/internal/otel/config.ts +3 -3
- package/src/internal/otel/runtime.ts +14 -14
- package/src/internal/peer-connections.ts +2 -2
- package/src/internal/platform-schedule-sync.ts +1 -1
- package/src/internal/platform-timers.ts +1 -1
- package/src/internal/playground/static.ts +2 -2
- package/src/internal/playground/toolchain.ts +2 -2
- package/src/internal/playground-proxy.ts +3 -3
- package/src/internal/process-memory-telemetry.ts +1 -1
- package/src/internal/reminder-runner.ts +8 -10
- package/src/internal/reminder-store.ts +1 -1
- package/src/internal/request-error-status.ts +9 -0
- package/src/internal/resolved-connections.ts +8 -8
- package/src/internal/result-output.ts +62 -5
- package/src/internal/router.ts +4 -4
- package/src/internal/run-client.ts +3 -3
- package/src/internal/schedule-runner.ts +6 -6
- package/src/internal/scm/pr-url.ts +11 -2
- package/src/internal/sdk-runner.ts +15 -29
- package/src/internal/serve-restart.ts +1 -1
- package/src/internal/server.ts +97 -115
- package/src/internal/session-cost.ts +3 -3
- package/src/internal/session-engine.ts +517 -445
- package/src/internal/session-run-log.ts +4 -6
- package/src/internal/session-store.ts +213 -39
- package/src/internal/sessions-client.ts +3 -3
- package/src/internal/slack-thread-key.ts +11 -0
- package/src/internal/sleep.ts +1 -1
- package/src/internal/storage-coordinator.ts +122 -96
- package/src/internal/storage-roles.ts +4 -9
- package/src/internal/storage.ts +1 -0
- package/src/internal/store-mirror.ts +4 -4
- package/src/internal/terminal-style.ts +2 -2
- package/src/internal/tool-result.ts +3 -3
- package/src/internal/trajectory.ts +7 -7
- package/src/internal/turn-governor.ts +2 -2
- package/src/internal/turn-outbox.ts +1 -1
- package/src/internal/update-check.ts +2 -2
- package/src/internal/v2-hosting.ts +14 -0
- package/src/internal/workspace.ts +17 -17
- package/src/kv/memory-kv.ts +9 -7
- package/src/kv.ts +4 -7
- package/src/otel-public.ts +24 -0
- package/src/otel.ts +7 -2
- package/src/prompt.ts +1 -1
- package/src/result.ts +10 -8
- package/src/storage-backends/cursor-hosted-v2.ts +6 -9
- package/src/storage-backends/cursor-hosted.ts +6 -60
- package/src/storage-backends/file-kv.ts +17 -58
- package/src/storage-protocol.ts +3 -17
- package/src/storage.ts +32 -108
- package/src/types.ts +101 -73
- package/templates/agentic-owners/agent/channels/github.ts +3 -6
- package/templates/agentic-owners/agent/lib/github.ts +5 -5
- package/templates/agentic-owners/agent/lib/owners/decision.ts +13 -10
- package/templates/agentic-owners/agent/lib/owners/handles.ts +2 -2
- package/templates/agentic-owners/agent/lib/owners/match.ts +3 -3
- package/templates/agentic-owners/agent/lib/owners/matching.ts +1 -1
- package/templates/agentic-owners/agent/lib/owners/parse.ts +4 -9
- package/templates/agentic-owners/agent/lib/owners/prompt.ts +1 -1
- package/templates/agentic-owners/agent/lib/review.ts +37 -30
- package/templates/agentic-owners/evals/owners.eval.ts +2 -2
- package/templates/agentic-owners/package.json +1 -1
- package/templates/agents-md/agent/lib/collect.ts +16 -10
- package/templates/agents-md/agent/lib/config.ts +1 -1
- package/templates/agents-md/agent/tools/apply_agents.ts +10 -8
- package/templates/agents-md/package.json +1 -1
- package/templates/code-wiki/agent/channels/github.ts +4 -7
- package/templates/code-wiki/agent/lib/repos.ts +1 -1
- package/templates/code-wiki/agent/tools/apply_wiki.ts +3 -4
- package/templates/code-wiki/package.json +1 -1
- package/templates/demo/README.md +10 -6
- package/templates/demo/agent/channels/github.ts +2 -0
- package/templates/demo/agent/channels/queue.ts +6 -2
- package/templates/demo/agent/lib/collect.ts +6 -2
- package/templates/demo/agent/lib/repos.ts +5 -0
- package/templates/demo/agent/tools/record_demo.ts +1 -1
- package/templates/demo/evals/demo.eval.ts +1 -5
- package/templates/demo/init.json +25 -0
- package/templates/demo/package.json +1 -1
- package/templates/grokbot-agents/package.json +1 -1
- package/templates/pr-autofixer/agent/channels/github.ts +16 -13
- package/templates/pr-autofixer/agent/lib/merge-watch.ts +2 -4
- package/templates/pr-autofixer/agent/lib/repos.ts +2 -2
- package/templates/pr-autofixer/agent/lib/webhook-routing.ts +1 -1
- package/templates/pr-autofixer/package.json +1 -1
- package/templates/security-help/agent/lib/repos.ts +1 -1
- package/templates/security-help/package.json +1 -1
- package/templates/security-reviewer/agent/lib/repos.ts +1 -1
- package/templates/security-reviewer/agent/tools/post_findings.ts +1 -3
- package/templates/security-reviewer/package.json +1 -1
- package/templates/triage/agent/lib/actuate.ts +26 -41
- package/templates/triage/agent/lib/parse-queue-event.ts +2 -1
- package/templates/triage/agent/lib/verify-webhook.ts +10 -5
- package/templates/triage/agent/tools/record_triage.ts +1 -4
- package/templates/triage/package.json +1 -1
- package/dist/ab.d.ts +0 -209
- package/dist/ab.d.ts.map +0 -1
- package/dist/ab.js +0 -246
- package/dist/client.d.ts +0 -14
- package/dist/client.d.ts.map +0 -1
- package/dist/client.js +0 -12
- package/dist/docs/ab.html +0 -80
- package/dist/docs/ab.md +0 -332
- package/dist/docs/assets/ab.md.mlVgqvSk.js +0 -54
- package/dist/docs/assets/ab.md.mlVgqvSk.lean.js +0 -1
- package/dist/docs/assets/app.BASKM3M4.js +0 -1
- package/dist/docs/assets/chunks/@localSearchIndexroot.BHZYsNVi.js +0 -1
- package/dist/docs/assets/chunks/framework.BCISBCiQ.js +0 -19
- package/dist/docs/assets/concepts.md.DgEcZOfT.js +0 -1
- package/dist/docs/assets/concepts.md.DgEcZOfT.lean.js +0 -1
- package/dist/docs/assets/evals.md.C1ekS3k2.js +0 -85
- package/dist/docs/assets/evals.md.C1ekS3k2.lean.js +0 -1
- package/dist/docs/assets/guides_agent-to-agent.md.BDb0t1QV.js +0 -10
- package/dist/docs/assets/guides_agent-to-agent.md.BDb0t1QV.lean.js +0 -1
- package/dist/docs/assets/guides_grokbot-agents.md.DyV-WArv.js +0 -9
- package/dist/docs/assets/guides_human-in-the-loop.md.By1G2T3_.js +0 -28
- package/dist/docs/assets/guides_human-in-the-loop.md.By1G2T3_.lean.js +0 -1
- package/dist/docs/assets/hillclimbing.md.CpTGTCle.js +0 -4
- package/dist/docs/assets/hillclimbing.md.CpTGTCle.lean.js +0 -1
- package/dist/docs/assets/index.md.BjH1w2ZW.js +0 -5
- package/dist/docs/assets/index.md.BjH1w2ZW.lean.js +0 -1
- package/dist/docs/assets/quickstart.md.DdQOF7Y8.lean.js +0 -1
- package/dist/docs/assets/reference_project-layout.md.DuBu9a96.js +0 -19
- package/dist/docs/assets/reference_result.md.BK5SxDrf.js +0 -19
- package/dist/docs/assets/reference_result.md.BK5SxDrf.lean.js +0 -1
- package/dist/docs/assets/reference_sessions.md.CueyOHSL.js +0 -1
- package/dist/docs/assets/scaffolding-agents.md.Kctn3OVb.js +0 -1
- package/dist/docs/assets/scaffolding-agents.md.Kctn3OVb.lean.js +0 -1
- package/dist/docs/assets/skills_ab.md.CsFNatVx.js +0 -26
- package/dist/docs/assets/skills_ab.md.CsFNatVx.lean.js +0 -1
- package/dist/docs/assets/skills_create-agent.md.Q3h6Je-e.js +0 -8
- package/dist/docs/assets/skills_create-agent.md.Q3h6Je-e.lean.js +0 -1
- package/dist/docs/assets/skills_debug.md.CVjCXMFF.js +0 -1
- package/dist/docs/assets/skills_debug.md.CVjCXMFF.lean.js +0 -1
- package/dist/docs/assets/skills_evals.md.BhovOvrl.js +0 -25
- package/dist/docs/assets/skills_evals.md.BhovOvrl.lean.js +0 -1
- package/dist/docs/assets/skills_framework-map.md.D-tFZhFS.js +0 -1
- package/dist/docs/assets/skills_framework-map.md.D-tFZhFS.lean.js +0 -1
- package/dist/docs/assets/skills_github.md.hgFX_oKY.js +0 -16
- package/dist/docs/assets/skills_github.md.hgFX_oKY.lean.js +0 -1
- package/dist/docs/assets/skills_hillclimb.md.B_zJerxA.js +0 -7
- package/dist/docs/assets/skills_hillclimb.md.B_zJerxA.lean.js +0 -1
- package/dist/docs/assets/skills_index.md.DKwIxzGg.js +0 -1
- package/dist/docs/assets/skills_index.md.DKwIxzGg.lean.js +0 -1
- package/dist/docs/assets/skills_mcp-auth.md.DGvFP3HE.js +0 -18
- package/dist/docs/assets/skills_mcp-auth.md.DGvFP3HE.lean.js +0 -1
- package/dist/docs/assets/skills_otel.md.B5Ddv1xH.js +0 -8
- package/dist/docs/assets/skills_otel.md.B5Ddv1xH.lean.js +0 -1
- package/dist/docs/assets/skills_setup-slack.md.BBgx8lUz.js +0 -20
- package/dist/docs/assets/skills_setup-slack.md.BBgx8lUz.lean.js +0 -1
- package/dist/docs/assets/storage.md.BOHeqk2M.js +0 -30
- package/dist/docs/assets/storage.md.BOHeqk2M.lean.js +0 -1
- package/dist/docs/assets/templates_agents-md.md.CXSMZljE.js +0 -2
- package/dist/docs/assets/templates_agents-md.md.CXSMZljE.lean.js +0 -1
- package/dist/docs/assets/templates_code-wiki.md.CDYZIBFN.js +0 -2
- package/dist/docs/assets/templates_code-wiki.md.CDYZIBFN.lean.js +0 -1
- package/dist/docs/assets/templates_demo.md.BeQX9V3H.js +0 -4
- package/dist/docs/assets/templates_demo.md.BeQX9V3H.lean.js +0 -1
- package/dist/docs/assets/templates_grokbot-agents.md.c1s6Flp9.js +0 -3
- package/dist/docs/assets/templates_grokbot-agents.md.c1s6Flp9.lean.js +0 -1
- package/dist/docs/assets/templates_security-help.md.C3Ny_Qr2.js +0 -4
- package/dist/docs/assets/templates_security-help.md.C3Ny_Qr2.lean.js +0 -1
- package/dist/docs/concepts.html +0 -27
- package/dist/docs/concepts.md +0 -168
- package/dist/docs/design/filesystem.md +0 -376
- package/dist/docs/design/runtime-abstraction.md +0 -1756
- package/dist/docs/guides/human-in-the-loop.html +0 -54
- package/dist/docs/guides/human-in-the-loop.md +0 -126
- package/dist/docs/reference/result.html +0 -45
- package/dist/docs/reference/result.md +0 -89
- package/dist/docs/scaffolding-agents.html +0 -27
- package/dist/docs/scaffolding-agents.md +0 -130
- package/dist/docs/skills/ab.html +0 -52
- package/dist/docs/skills/ab.md +0 -50
- package/dist/docs/skills/create-agent.html +0 -34
- package/dist/docs/skills/create-agent.md +0 -160
- package/dist/docs/skills/debug.html +0 -27
- package/dist/docs/skills/debug.md +0 -36
- package/dist/docs/skills/evals.html +0 -51
- package/dist/docs/skills/evals.md +0 -99
- package/dist/docs/skills/framework-map.html +0 -27
- package/dist/docs/skills/framework-map.md +0 -100
- package/dist/docs/skills/github.html +0 -42
- package/dist/docs/skills/github.md +0 -93
- package/dist/docs/skills/hillclimb.html +0 -33
- package/dist/docs/skills/hillclimb.md +0 -55
- package/dist/docs/skills/index.html +0 -27
- package/dist/docs/skills/index.md +0 -21
- package/dist/docs/skills/mcp-auth.html +0 -44
- package/dist/docs/skills/mcp-auth.md +0 -76
- package/dist/docs/skills/otel.html +0 -34
- package/dist/docs/skills/otel.md +0 -53
- package/dist/docs/skills/setup-slack.html +0 -46
- package/dist/docs/skills/setup-slack.md +0 -141
- package/dist/docs/storage.html +0 -56
- package/dist/docs/storage.md +0 -176
- package/dist/docs/templates/agents-md.html +0 -28
- package/dist/docs/templates/agents-md.md +0 -105
- package/dist/docs/templates/code-wiki.html +0 -28
- package/dist/docs/templates/code-wiki.md +0 -91
- package/dist/docs/templates/demo.html +0 -30
- package/dist/docs/templates/demo.md +0 -80
- package/dist/docs/templates/grokbot-agents.html +0 -29
- package/dist/docs/templates/grokbot-agents.md +0 -48
- package/dist/docs/templates/security-help.html +0 -30
- package/dist/docs/templates/security-help.md +0 -65
- package/dist/internal/ab-collector.d.ts +0 -44
- package/dist/internal/ab-collector.d.ts.map +0 -1
- package/dist/internal/ab-collector.js +0 -142
- package/dist/internal/ab-fold.d.ts +0 -36
- package/dist/internal/ab-fold.d.ts.map +0 -1
- package/dist/internal/ab-fold.js +0 -175
- package/dist/internal/ab-snapshot.d.ts +0 -68
- package/dist/internal/ab-snapshot.d.ts.map +0 -1
- package/dist/internal/ab-snapshot.js +0 -208
- package/dist/internal/discovery/ab.d.ts +0 -9
- package/dist/internal/discovery/ab.d.ts.map +0 -1
- package/dist/internal/discovery/ab.js +0 -113
- package/dist/internal/tenant-slack/relay.d.ts +0 -75
- package/dist/internal/tenant-slack/relay.d.ts.map +0 -1
- package/dist/internal/tenant-slack/relay.js +0 -148
- package/dist/playground/assets/index-BMDqAeXu.js +0 -67
- package/dist/playground/assets/index-LUgJoWdL.css +0 -1
- package/docs/ab.md +0 -337
- package/docs/concepts.md +0 -173
- package/docs/design/filesystem.md +0 -376
- package/docs/design/runtime-abstraction.md +0 -1756
- package/docs/guides/human-in-the-loop.md +0 -131
- package/docs/reference/result.md +0 -94
- package/docs/scaffolding-agents.md +0 -135
- package/docs/skills/index.md +0 -26
- package/docs/storage.md +0 -181
- package/docs/templates/agents-md.md +0 -110
- package/docs/templates/code-wiki.md +0 -96
- package/docs/templates/demo.md +0 -85
- package/docs/templates/grokbot-agents.md +0 -53
- package/docs/templates/security-help.md +0 -70
- package/skills/ab/SKILL.md +0 -58
- package/src/ab.ts +0 -430
- package/src/client.ts +0 -23
- package/src/internal/ab-collector.ts +0 -200
- package/src/internal/ab-fold.ts +0 -232
- package/src/internal/ab-snapshot.ts +0 -331
- package/src/internal/discovery/ab.ts +0 -131
- package/src/internal/tenant-slack/relay.ts +0 -203
- package/templates/pr-autofixer/agent/storage.ts +0 -7
package/dist/docs/ab.html
DELETED
|
@@ -1,80 +0,0 @@
|
|
|
1
|
-
<!DOCTYPE html>
|
|
2
|
-
<html lang="en-US" dir="ltr">
|
|
3
|
-
<head>
|
|
4
|
-
<meta charset="utf-8">
|
|
5
|
-
<meta name="viewport" content="width=device-width,initial-scale=1">
|
|
6
|
-
<title>Live A/B metrics | Agent SDK</title>
|
|
7
|
-
<meta name="description" content="Assign sticky variants with defineAB, collect live performance metrics, and inspect per-arm results.">
|
|
8
|
-
<meta name="generator" content="VitePress v1.6.4">
|
|
9
|
-
<link rel="preload stylesheet" href="/docs/assets/style.DCD_zyg3.css" as="style">
|
|
10
|
-
<link rel="preload stylesheet" href="/docs/vp-icons.css" as="style">
|
|
11
|
-
|
|
12
|
-
<script type="module" src="/docs/assets/app.BASKM3M4.js"></script>
|
|
13
|
-
<link rel="preload" href="/docs/assets/inter-roman-latin.Di8DUHzh.woff2" as="font" type="font/woff2" crossorigin="">
|
|
14
|
-
<link rel="modulepreload" href="/docs/assets/chunks/theme.DbDZW-zb.js">
|
|
15
|
-
<link rel="modulepreload" href="/docs/assets/chunks/framework.BCISBCiQ.js">
|
|
16
|
-
<link rel="modulepreload" href="/docs/assets/ab.md.mlVgqvSk.lean.js">
|
|
17
|
-
<script id="check-dark-mode">(()=>{const e=localStorage.getItem("vitepress-theme-appearance")||"auto",a=window.matchMedia("(prefers-color-scheme: dark)").matches;(!e||e==="auto"?a:e==="dark")&&document.documentElement.classList.add("dark")})();</script>
|
|
18
|
-
<script id="check-mac-os">document.documentElement.classList.toggle("mac",/Mac|iPhone|iPod|iPad/i.test(navigator.platform));</script>
|
|
19
|
-
<link rel="alternate" type="text/plain" href="/docs/llms.txt">
|
|
20
|
-
<link rel="alternate" type="text/markdown" href="/docs/ab.md">
|
|
21
|
-
</head>
|
|
22
|
-
<body>
|
|
23
|
-
<div id="app"><div class="Layout" data-v-990b7706><!--[--><!--]--><!--[--><span tabindex="-1" data-v-0b74bec0></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-0b74bec0>Skip to content</a><!--]--><!----><header class="VPNav" data-v-990b7706 data-v-af996e33><div class="VPNavBar" data-v-af996e33 data-v-c7f322eb><div class="wrapper" data-v-c7f322eb><div class="container" data-v-c7f322eb><div class="title" data-v-c7f322eb><div class="VPNavBarTitle has-sidebar" data-v-c7f322eb data-v-d1664c59><a class="title" href="/docs/" data-v-d1664c59><!--[--><!--]--><!----><span data-v-d1664c59>Agent SDK</span><!--[--><!--[--><!--[--><!--[--><span class="agent-sdk-version" title="@cursor/july 0.1.108" data-v-c26a5f4f>0.1.108</span><!--]--><!--]--><!--]--><!--]--></a></div></div><div class="content" data-v-c7f322eb><div class="content-body" data-v-c7f322eb><!--[--><!--]--><div class="VPNavBarSearch search" data-v-c7f322eb><!--[--><!----><div id="local-search"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><span class="vp-icon DocSearch-Search-Icon"></span><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"><kbd class="DocSearch-Button-Key"></kbd><kbd class="DocSearch-Button-Key">K</kbd></span></button></div><!--]--></div><nav aria-labelledby="main-nav-aria-label" class="VPNavBarMenu menu" data-v-c7f322eb data-v-ab749b05><span id="main-nav-aria-label" class="visually-hidden" data-v-ab749b05> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/quickstart.html" tabindex="0" data-v-ab749b05 data-v-ef8d136f><!--[--><span data-v-ef8d136f>Quickstart</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/guides/webhooks.html" tabindex="0" data-v-ab749b05 data-v-ef8d136f><!--[--><span data-v-ef8d136f>Guides</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/templates/demo.html" tabindex="0" data-v-ab749b05 data-v-ef8d136f><!--[--><span data-v-ef8d136f>Templates</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/reference/project-layout.html" tabindex="0" data-v-ab749b05 data-v-ef8d136f><!--[--><span data-v-ef8d136f>Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-c7f322eb data-v-7c6c0ede><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-7c6c0ede data-v-87b8a6bb data-v-9f798512><span class="check" data-v-9f798512><span class="icon" data-v-9f798512><!--[--><span class="vpi-sun sun" data-v-87b8a6bb></span><span class="vpi-moon moon" data-v-87b8a6bb></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-c7f322eb data-v-e53d4296 data-v-79fc383b><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-79fc383b><span class="vpi-more-horizontal icon" data-v-79fc383b></span></button><div class="menu" data-v-79fc383b><div class="VPMenu" data-v-79fc383b data-v-0d780c53><!----><!--[--><!--[--><!----><div class="group" data-v-e53d4296><div class="item appearance" data-v-e53d4296><p class="label" data-v-e53d4296>Appearance</p><div class="appearance-action" data-v-e53d4296><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-e53d4296 data-v-87b8a6bb data-v-9f798512><span class="check" data-v-9f798512><span class="icon" data-v-9f798512><!--[--><span class="vpi-sun sun" data-v-87b8a6bb></span><span class="vpi-moon moon" data-v-87b8a6bb></span><!--]--></span></span></button></div></div></div><!----><!--]--><!--]--></div></div></div><!--[--><!--]--><button type="button" class="VPNavBarHamburger hamburger" aria-label="mobile navigation" aria-expanded="false" aria-controls="VPNavScreen" data-v-c7f322eb data-v-edf597df><span class="container" data-v-edf597df><span class="top" data-v-edf597df></span><span class="middle" data-v-edf597df></span><span class="bottom" data-v-edf597df></span></span></button></div></div></div></div><div class="divider" data-v-c7f322eb><div class="divider-line" data-v-c7f322eb></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-990b7706 data-v-054265d6><div class="container" data-v-054265d6><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-054265d6><span class="vpi-align-left menu-icon" data-v-054265d6></span><span class="menu-text" data-v-054265d6>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-054265d6 data-v-65e16bd4><button data-v-65e16bd4>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-990b7706 data-v-03069692><div class="curtain" data-v-03069692></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-03069692><span class="visually-hidden" id="sidebar-aria-label" data-v-03069692> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Getting started</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/quickstart.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Quickstart</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/scaffolding-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Scaffold an agent with Cursor</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/convert-automation.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Convert a Cursor Automation</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/concepts.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Concepts</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Templates</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/demo.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Demo agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/grokbot-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Grok Bot agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/code-wiki.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Code wiki</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/agents-md.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Living AGENTS.md</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/security-reviewer.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Security reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/security-help.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Security help</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/agentic-owners.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Agentic Owners</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/pr-autofixer.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>PR autofixer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/templates/triage.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Triage agent</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0 has-active" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Improving agents</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/building-with-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Building agents with agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/evals.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/ab.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Live A/B metrics</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/storage.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Storage</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/hillclimbing.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Hillclimbing</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0 collapsible collapsed" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Coding-agent skills</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-9a4aac52><span class="vpi-chevron-right caret-icon" data-v-9a4aac52></span></div></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/ab.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>ab</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/create-agent.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>create-agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/debug.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>debug</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/evals.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/framework-map.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>framework-map</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/github.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>github</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/hillclimb.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>hillclimb</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/mcp-auth.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>mcp-auth</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/otel.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>otel</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/skills/setup-slack.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>setup-slack</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Guides</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/webhooks.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Webhooks & custom channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/github.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>GitHub</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/slack.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Slack</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/human-in-the-loop.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Human-in-the-loop approvals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/agent-to-agent.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Agent-to-agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/mcp-oauth.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Host MCP OAuth</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/cloud-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Cursor cloud agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/grokbot-agents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Cursor Grok Bot agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/improve.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Self-improvement</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/guides/opentelemetry.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>OpenTelemetry</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Operating</h2><!----></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/deployment.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Deployment</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/troubleshooting.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Fix common problems</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-53da167f><section class="VPSidebarItem level-0 collapsible" data-v-53da167f data-v-9a4aac52><div class="item" role="button" tabindex="0" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><h2 class="text" data-v-9a4aac52>Reference</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-9a4aac52><span class="vpi-chevron-right caret-icon" data-v-9a4aac52></span></div></div><div class="items" data-v-9a4aac52><!--[--><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/project-layout.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Project layout</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/agent-config.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Agent config</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/instructions.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Instructions</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/tools.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Tools</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/prompt.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>prompt</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/skills.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Skills</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/connections.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>MCP Connections</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/subagents.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Subagents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/extensions.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Extensions</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/channels.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/schedules.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Schedules & reminders</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/hooks.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Hooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/artifacts.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Artifacts</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/result.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Turn result</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/sessions.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Sessions & streaming</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/playground.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>Playground</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/cli.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>CLI</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-9a4aac52><div class="item" data-v-9a4aac52><div class="indicator" data-v-9a4aac52></div><a class="VPLink link link" href="/docs/reference/http-api.html" data-v-9a4aac52><!--[--><p class="text" data-v-9a4aac52>HTTP API</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-990b7706 data-v-7a16121a><div class="VPDoc has-sidebar has-aside" data-v-7a16121a data-v-38549ef7><!--[--><!--]--><div class="container" data-v-38549ef7><div class="aside" data-v-38549ef7><div class="aside-curtain" data-v-38549ef7></div><div class="aside-container" data-v-38549ef7><div class="aside-content" data-v-38549ef7><div class="VPDocAside" data-v-38549ef7 data-v-da90486d><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-da90486d data-v-0895f2d7><div class="content" data-v-0895f2d7><div class="outline-marker" data-v-0895f2d7></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-0895f2d7>On this page</div><ul class="VPDocOutlineItem root" data-v-0895f2d7 data-v-0cae2091><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-da90486d></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-38549ef7><div class="content-container" data-v-38549ef7><!--[--><!--]--><main class="main" data-v-38549ef7><div style="position:relative;" class="vp-doc _docs_ab" data-v-38549ef7><div><h1 id="live-a-b-metrics" tabindex="-1">Live A/B metrics <a class="header-anchor" href="#live-a-b-metrics" aria-label="Permalink to "Live A/B metrics""></a></h1><p>Use <code>defineAB</code> to compare variants on live agent sessions. New sessions receive a sticky assignment in each enrolled experiment. The Agent SDK folds their durable event streams into tool, token, failure, and wall-time metrics. You can send cumulative samples to your metrics backend and inspect aggregates in the playground.</p><p><code>defineAB</code> compares live variants through sticky assignment, instruction overlays, optional tool branches, and cumulative metrics. Metric callbacks observe the result without approving, rejecting, or failing a turn. Use <a href="./evals.html">evals</a> for pass/fail regression checks on fixed inputs.</p><h2 id="choose-live-a-b-metrics-or-evals" tabindex="-1">Choose live A/B metrics or evals <a class="header-anchor" href="#choose-live-a-b-metrics-or-evals" aria-label="Permalink to "Choose live A/B metrics or evals""></a></h2><p>Both features read the session event stream, but they answer different questions.</p><table tabindex="0"><thead><tr><th></th><th>Live A/B metrics</th><th>Evals</th></tr></thead><tbody><tr><td>Question</td><td>How do variants compare on live sessions?</td><td>Does the agent still meet a fixed contract?</td></tr><tr><td>Location</td><td><code>agent/ab.ts</code> or <code>agent/ab/<name>.ts</code></td><td><code>evals/**/*.eval.ts</code></td></tr><tr><td>Input</td><td>Dev or production traffic</td><td>Frozen prompts and fixtures</td></tr><tr><td>Output</td><td>Cumulative metrics by session and arm</td><td>Pass/fail assertions</td></tr><tr><td>How it runs</td><td>Automatically on new live sessions</td><td><code>agent-sdk eval</code></td></tr></tbody></table><p>There is no <code>agent-sdk ab</code> command or assertion API.</p><h2 id="define-an-experiment" tabindex="-1">Define an experiment <a class="header-anchor" href="#define-an-experiment" aria-label="Permalink to "Define an experiment""></a></h2><p>Author one experiment in <code>agent/ab.ts</code>, add more under <code>agent/ab/<name>.ts</code>, or use both forms. Each file defines one experiment. The experiment name comes from <code>name</code> when set. Otherwise, the Agent SDK uses <code>ab</code> for <code>agent/ab.ts</code> and the file stem for files under <code>agent/ab/</code>.</p><div class="language-ts vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">ts</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;">// agent/ab/concise-weather.ts</span></span>
|
|
24
|
-
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">import</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> {</span></span>
|
|
25
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> defineAB,</span></span>
|
|
26
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> splitBySessionHash,</span></span>
|
|
27
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">} </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">from</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> "@cursor/july/ab"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">;</span></span>
|
|
28
|
-
<span class="line"></span>
|
|
29
|
-
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">export</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> default</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;"> defineAB</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">({</span></span>
|
|
30
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> name: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"concise-weather"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
31
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> variants: {</span></span>
|
|
32
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> control: {</span></span>
|
|
33
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> label: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"Baseline"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
34
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
|
|
35
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> treatment: {</span></span>
|
|
36
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> label: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"Short replies"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
37
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> description: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"Adds a one-paragraph response limit."</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
38
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> instructions: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"Keep weather replies to one short paragraph."</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
39
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
|
|
40
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
|
|
41
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> split: </span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">splitBySessionHash</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">({</span></span>
|
|
42
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> weights: { control: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">1</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, treatment: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">1</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
|
|
43
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> holdout: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">0.1</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
44
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> }),</span></span>
|
|
45
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> derive: {</span></span>
|
|
46
|
-
<span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;"> weatherCalls</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: (</span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70;">event</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">) </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">=></span></span>
|
|
47
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> event.type </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">===</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> "action.result"</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> &&</span></span>
|
|
48
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> event.data.toolName </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">===</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> "get_weather"</span></span>
|
|
49
|
-
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> ?</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> 1</span></span>
|
|
50
|
-
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> :</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> null</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
51
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
|
|
52
|
-
<span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;"> onSample</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(</span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70;">sample</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">) {</span></span>
|
|
53
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> console.</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">log</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(</span></span>
|
|
54
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> sample.experiment,</span></span>
|
|
55
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> sample.variant,</span></span>
|
|
56
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> sample.metrics.toolCalls,</span></span>
|
|
57
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> sample.metrics.wallTimeMs</span></span>
|
|
58
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> );</span></span>
|
|
59
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
|
|
60
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">});</span></span></code></pre></div><p>Every definition needs:</p><ul><li>At least two variants. Variant keys cannot be empty or contain <code>/</code> or <code>\</code>.</li><li>A <code>split</code> function that returns a variant key or <code>null</code>.</li><li>An <code>onSample</code> callback for completed or failed turns.</li></ul><p><code>label</code> and <code>description</code> appear with the arm in result surfaces. <code>instructions</code> changes the prompt for sessions in that arm. <code>derive</code> adds custom counters.</p><p>Duplicate experiment names are validation errors. Check discovery before you serve:</p><div class="language-bash vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">bash</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">agent-sdk</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> validate</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --dir</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> .</span></span>
|
|
61
|
-
<span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">agent-sdk</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> info</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --dir</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> .</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> --json</span></span></code></pre></div><p>The <code>abs</code> field in <code>info</code> lists the discovered experiment names.</p><h2 id="assign-sticky-variants" tabindex="-1">Assign sticky variants <a class="header-anchor" href="#assign-sticky-variants" aria-label="Permalink to "Assign sticky variants""></a></h2><p>Enrollment happens once, when a live session is created and before its first turn:</p><ol><li>The Agent SDK records <code>session.started</code>.</li><li>Each experiment runs its <code>split</code> function.</li><li>The Agent SDK records one durable <code>ab.assigned</code> event per experiment.</li><li>The selected arms become available on <code>session.abs</code>.</li><li>Variant instruction overlays reach the first model turn.</li></ol><p>A split can return a variant key or <code>null</code>. A null assignment is a sticky skip for that experiment. It increments the experiment's <code>skipped</code> total, still appears in the snapshot's <code>sessions</code> list with <code>variant: null</code>, and does not collect arm metrics or call <code>onSample</code>.</p><p>Use the split helper that matches your rollout:</p><table tabindex="0"><thead><tr><th>Helper</th><th>Behavior</th></tr></thead><tbody><tr><td><code>splitBySessionHash({ weights?, holdout?, salt? })</code></td><td>Hashes the session id into a reproducible arm; the recommended default</td></tr><tr><td><code>splitByRandom({ weights?, holdout? })</code></td><td>Draws once when the session starts, then persists the result</td></tr><tr><td><code>splitAlways("control")</code></td><td>Pins every new session to one arm</td></tr><tr><td><code>splitNone()</code></td><td>Skips every new session without deleting the experiment</td></tr><tr><td><code>splitIf(predicate, inner)</code></td><td>Runs <code>inner</code> only when the predicate passes</td></tr><tr><td>Custom <code>split(ctx)</code></td><td>Returns a declared variant key or <code>null</code></td></tr></tbody></table><p>The split context includes the agent name, channel id, session info, experiment name, and declared variant keys. For example, enroll only Slack sessions:</p><div class="language-ts vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">ts</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">split</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;">splitIf</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">(</span></span>
|
|
62
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> (</span><span style="--shiki-light:#E36209;--shiki-dark:#FFAB70;">ctx</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">) </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">=></span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> ctx.channel.id </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">===</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> "slack"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
63
|
-
<span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;"> splitBySessionHash</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">()</span></span>
|
|
64
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">),</span></span></code></pre></div><p>Weights default to equal. Non-positive weights leave an arm out of the draw, and at least one arm must have a positive weight. <code>holdout</code> is the fraction of sessions assigned <code>null</code>, from <code>0</code> through <code>1</code>. Change <code>salt</code> to reshuffle future hash assignments without renaming the experiment.</p><p>If a custom split throws or returns an unknown variant, the Agent SDK logs the error and records <code>variant: null</code>. The failed decision becomes a sticky skip instead of breaking the session.</p><p>Enrollment only applies to new sessions. Adding an experiment does not assign existing conversations. Follow-ups keep the session's original arms. Keep experiment names and variant keys stable while you collect and compare results.</p><h2 id="change-behavior-by-variant" tabindex="-1">Change behavior by variant <a class="header-anchor" href="#change-behavior-by-variant" aria-label="Permalink to "Change behavior by variant""></a></h2><p>Variant instructions are appended to the agent's base instructions. Local sessions receive the merged instructions in <code>AGENTS.md</code> before every turn. Cloud sessions receive them in the first-turn preamble only. For cloud follow-ups, branch through <code>session.abs</code> when the arm must remain visible to deterministic behavior.</p><p>Tools can branch on the assignment through <code>ctx.session.abs</code>. Hooks can read the same field for logging or export:</p><div class="language-ts vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">ts</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">const</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;"> treatment</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> =</span></span>
|
|
65
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> ctx.session.abs?.[</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">"concise-weather"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">] </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">===</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> "treatment"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">;</span></span>
|
|
66
|
-
<span class="line"></span>
|
|
67
|
-
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">if</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> (treatment) {</span></span>
|
|
68
|
-
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> return</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> conciseWeatherResult;</span></span>
|
|
69
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span>
|
|
70
|
-
<span class="line"></span>
|
|
71
|
-
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">return</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> baselineWeatherResult;</span></span></code></pre></div><p>This makes the assignment available to deterministic code as well as the model prompt. Use both patterns together when one experiment must steer the prompt and host code at once.</p><p><code>defineAB</code> does not select a different model or runtime for each arm. Keep those settings in <code>agent/agent.ts</code>, or write explicit host logic when your experiment needs another behavior lever.</p><p>The split and selected arm can affect agent behavior. <code>derive</code> and <code>onSample</code> only observe the resulting event stream. Errors in either callback are logged and never fail the turn.</p><h2 id="collect-built-in-and-custom-metrics" tabindex="-1">Collect built-in and custom metrics <a class="header-anchor" href="#collect-built-in-and-custom-metrics" aria-label="Permalink to "Collect built-in and custom metrics""></a></h2><p>Metrics accumulate for each session and experiment. When one session joins several experiments, every enrolled experiment folds the same turn and tool events into its own counters.</p><table tabindex="0"><thead><tr><th>Metric</th><th>How the Agent SDK calculates it</th></tr></thead><tbody><tr><td><code>turns</code></td><td>Adds one on <code>turn.completed</code> or <code>turn.failed</code></td></tr><tr><td><code>turnFailures</code></td><td>Adds one on <code>turn.failed</code></td></tr><tr><td><code>toolCalls</code></td><td>Adds one for each <code>action.result</code></td></tr><tr><td><code>toolErrors</code></td><td>Adds one when <code>action.result.data.isError</code> is true</td></tr><tr><td><code>inputTokens</code>, <code>outputTokens</code></td><td>Adds usage from completed turns</td></tr><tr><td><code>cacheReadTokens</code>, <code>cacheWriteTokens</code></td><td>Adds cache usage from completed turns</td></tr><tr><td><code>costUsd</code></td><td>Sums the estimated turn cost recorded on <code>turn.completed</code> (turns whose model has no known rates contribute 0)</td></tr><tr><td><code>wallTimeMs</code></td><td>Sums the time from <code>turn.started</code> to its completed or failed event</td></tr><tr><td><code>custom</code></td><td>Sums finite numeric deltas returned by <code>derive</code></td></tr></tbody></table><p><code>onSample</code> fires after every <code>turn.completed</code> and <code>turn.failed</code> event for an enrolled arm. The sample contains:</p><table tabindex="0"><thead><tr><th>Field</th><th>Value</th></tr></thead><tbody><tr><td><code>experiment</code></td><td>Experiment name</td></tr><tr><td><code>variant</code>, <code>variantLabel?</code></td><td>Sticky arm and optional display label</td></tr><tr><td><code>sessionId</code>, <code>channelId</code></td><td>Source session</td></tr><tr><td><code>metrics</code></td><td>Cumulative metrics through this turn</td></tr><tr><td><code>reason</code></td><td><code>turn.completed</code> or <code>turn.failed</code></td></tr><tr><td><code>at</code></td><td>Terminal event timestamp</td></tr></tbody></table><p>The metrics are cumulative, not per-turn deltas. A second sample from the same session includes the first turn's counts.</p><p>Each <code>derive</code> extractor runs on every session event for its enrolled experiment, including streamed <code>message.appended</code> events. Keep it synchronous and cheap. Return a finite number to add a delta, or <code>null</code> to skip the event. Send samples to your metrics service from <code>onSample</code>; do not perform network or disk work in <code>derive</code>.</p><p>Skipped sessions never call <code>onSample</code>. Errors from <code>derive</code> or <code>onSample</code> are logged, then metric collection continues.</p><h2 id="inspect-assignments-and-results" tabindex="-1">Inspect assignments and results <a class="header-anchor" href="#inspect-assignments-and-results" aria-label="Permalink to "Inspect assignments and results""></a></h2><p>Open the playground's <strong>A/Bs</strong> tab to see aggregate arm totals and per-session assignments. The tab reads <code>GET /v1/abs</code>.</p><p>The response has two views of the same durable data:</p><table tabindex="0"><thead><tr><th>Field</th><th>Contents</th></tr></thead><tbody><tr><td><code>experiments</code></td><td>Declared variants, skipped-session count, arm session counts, and aggregate metrics</td></tr><tr><td><code>sessions</code></td><td>Visible sessions with their assignments and cumulative metrics</td></tr></tbody></table><p><code>GET /v1/abs</code> returns sessions visible to the current principal by default. In <code>--dev</code>, loopback requests include every session. Add <code>--allow-anonymous</code> to include every session from non-loopback callers too.</p><p>The session event stream is the source of truth for assignment + fold. <code>GET /v1/abs</code> recomputes aggregates from those logs. Any <code>agent/storage.ts</code> exports samples and snapshots durably: an authored <code>abs</code> table when the backend has a native shape for it, or the table derived over the KV core otherwise. See <a href="./storage.html#eval-and-a-b-tables">Storage</a>.</p><h2 id="configure-the-playground-fold-window" tabindex="-1">Configure the playground fold window <a class="header-anchor" href="#configure-the-playground-fold-window" aria-label="Permalink to "Configure the playground fold window""></a></h2><p>Assignments and foldable metrics already persist in each session's event stream. The optional <code>agent/ab.config.ts</code> only caps how many sessions the playground and <code>GET /v1/abs</code> fold:</p><div class="language-ts vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">ts</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">import</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> { defineABConfig } </span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">from</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;"> "@cursor/july/ab"</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">;</span></span>
|
|
72
|
-
<span class="line"></span>
|
|
73
|
-
<span class="line"><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;">export</span><span style="--shiki-light:#D73A49;--shiki-dark:#F97583;"> default</span><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0;"> defineABConfig</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">({</span></span>
|
|
74
|
-
<span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D;"> // Optional. Defaults to 200. Only affects GET /v1/abs / A/Bs tab.</span></span>
|
|
75
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> maxPlaygroundSessions: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">500</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
|
|
76
|
-
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">});</span></span></code></pre></div><p><code>maxPlaygroundSessions</code> keeps the newest sessions in the fold. It does not prune session logs or change assignment. For export to S3, a DB, or your metrics vendor, send samples from <code>onSample</code> or declare a storage <code>abs</code> table.</p><h2 id="keep-assignments-durable" tabindex="-1">Keep assignments durable <a class="header-anchor" href="#keep-assignments-durable" aria-label="Permalink to "Keep assignments durable""></a></h2><p>The append-only event stream is the source of truth. Each <code>ab.assigned</code> event persists a variant key or null skip. Built-in metrics come from the turn and tool events that follow it.</p><p>After a server restart or a parked session resumes, the live collector replays the stream to rebuild cumulative counters. Replay does not call <code>onSample</code> (or write to the storage <code>abs</code> table) for historical turns. Only a new completed or failed turn emits another sample.</p><p>The snapshot API also replays <code>derive</code> across the full stream, so custom totals match the current extractor. Changing a derive function can change historical snapshot totals. Treat metric definitions as versioned experiment code.</p><h2 id="keep-eval-traffic-separate" tabindex="-1">Keep eval traffic separate <a class="header-anchor" href="#keep-eval-traffic-separate" aria-label="Permalink to "Keep eval traffic separate""></a></h2><p>Sessions created by <code>agent-sdk eval</code> and the playground Evals runner use <code>purpose: "eval"</code>. They skip A/B enrollment entirely:</p><ul><li>No split function runs.</li><li>No <code>ab.assigned</code> event is recorded.</li><li>No <code>onSample</code> callback fires.</li><li>The session is omitted from <code>GET /v1/abs</code>.</li></ul><p>Ordinary chat, <code>agent-sdk run</code>, Slack, GitHub, and other channel sessions use the live purpose. You do not need <code>splitIf</code> to exclude eval traffic.</p><h2 id="know-the-boundaries" tabindex="-1">Know the boundaries <a class="header-anchor" href="#know-the-boundaries" aria-label="Permalink to "Know the boundaries""></a></h2><p><code>defineAB</code> provides sticky assignment, variant instructions, <code>session.abs</code> for tools, cumulative metrics, and local inspection. It does not provide:</p><ul><li>A test command, assertion API, or pass/fail result</li><li>Statistical significance calculations</li><li>An experiment rollout or lifecycle service</li><li>Per-variant model or runtime configuration</li><li>A built-in analytics warehouse (bring your own via <code>onSample</code> or the storage <code>abs</code> table)</li></ul><p>Use <a href="./evals.html">evals</a> to protect known behavior. Use <code>onSample</code> or a storage <code>abs</code> table when you need sample/snapshot exports beyond the session event log.</p><h2 id="what-s-next" tabindex="-1">What's next <a class="header-anchor" href="#what-s-next" aria-label="Permalink to "What's next""></a></h2><p>Continue with these pages:</p><ul><li><a href="./evals.html">Evals</a>: pass/fail regression checks on fixed inputs</li><li><a href="./hillclimbing.html">Hillclimbing</a>: improve an agent against fixed fixtures</li><li><a href="./reference/hooks.html">Hooks</a>: other event-stream consumers</li><li><a href="./reference/sessions.html">Sessions and streaming</a>: the <code>ab.assigned</code> event and durable log</li><li><a href="./reference/playground.html">Playground</a>: the A/Bs tab</li><li><a href="./reference/http-api.html">HTTP API</a>: <code>GET /v1/abs</code></li><li><a href="./skills/ab.html">Live A/B metrics skill</a>: have a coding agent wire an experiment</li></ul></div></div></main><footer class="VPDocFooter" data-v-38549ef7 data-v-215f93e6><!--[--><!--]--><!----><nav class="prev-next" aria-labelledby="doc-footer-aria-label" data-v-215f93e6><span class="visually-hidden" id="doc-footer-aria-label" data-v-215f93e6>Pager</span><div class="pager" data-v-215f93e6><a class="VPLink link pager-link prev" href="/docs/evals.html" data-v-215f93e6><!--[--><span class="desc" data-v-215f93e6>Previous page</span><span class="title" data-v-215f93e6>Evals</span><!--]--></a></div><div class="pager" data-v-215f93e6><a class="VPLink link pager-link next" href="/docs/storage.html" data-v-215f93e6><!--[--><span class="desc" data-v-215f93e6>Next page</span><span class="title" data-v-215f93e6>Storage</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
|
|
77
|
-
<script>window.__VP_HASH_MAP__=JSON.parse("{\"ab.md\":\"mlVgqvSk\",\"building-with-agents.md\":\"CUSWxlP_\",\"concepts.md\":\"DgEcZOfT\",\"deployment.md\":\"JenwuCCB\",\"evals.md\":\"C1ekS3k2\",\"guides_agent-to-agent.md\":\"BDb0t1QV\",\"guides_cloud-agents.md\":\"BsloyHdY\",\"guides_convert-automation.md\":\"B4sjlodG\",\"guides_github.md\":\"BH33UEBJ\",\"guides_grokbot-agents.md\":\"DyV-WArv\",\"guides_human-in-the-loop.md\":\"By1G2T3_\",\"guides_improve.md\":\"BGVk32bK\",\"guides_mcp-oauth.md\":\"Dp6cDP7f\",\"guides_opentelemetry.md\":\"SCRMskno\",\"guides_slack.md\":\"D4RVMM4G\",\"guides_webhooks.md\":\"DKdA43Qm\",\"hillclimbing.md\":\"CpTGTCle\",\"index.md\":\"BjH1w2ZW\",\"quickstart.md\":\"DdQOF7Y8\",\"reference_agent-config.md\":\"CvoL6pof\",\"reference_artifacts.md\":\"Dior32Qw\",\"reference_channels.md\":\"D-qTqwcq\",\"reference_cli.md\":\"Ca26u0Es\",\"reference_connections.md\":\"BojkC6c5\",\"reference_extensions.md\":\"CPWt00ds\",\"reference_hooks.md\":\"Ddt5DdgJ\",\"reference_http-api.md\":\"oySXBO8o\",\"reference_instructions.md\":\"CR7XSsGk\",\"reference_playground.md\":\"4myJPxrf\",\"reference_project-layout.md\":\"DuBu9a96\",\"reference_prompt.md\":\"DnaD5dNK\",\"reference_result.md\":\"BK5SxDrf\",\"reference_schedules.md\":\"DI_JrHgq\",\"reference_sessions.md\":\"CueyOHSL\",\"reference_skills.md\":\"l2ezAcaN\",\"reference_subagents.md\":\"CfsIloPm\",\"reference_tools.md\":\"aGrn99hP\",\"scaffolding-agents.md\":\"Kctn3OVb\",\"skills_ab.md\":\"CsFNatVx\",\"skills_create-agent.md\":\"Q3h6Je-e\",\"skills_debug.md\":\"CVjCXMFF\",\"skills_evals.md\":\"BhovOvrl\",\"skills_framework-map.md\":\"D-tFZhFS\",\"skills_github.md\":\"hgFX_oKY\",\"skills_hillclimb.md\":\"B_zJerxA\",\"skills_index.md\":\"DKwIxzGg\",\"skills_mcp-auth.md\":\"DGvFP3HE\",\"skills_otel.md\":\"B5Ddv1xH\",\"skills_setup-slack.md\":\"BBgx8lUz\",\"storage.md\":\"BOHeqk2M\",\"templates_agentic-owners.md\":\"BZSH4N9z\",\"templates_agents-md.md\":\"CXSMZljE\",\"templates_code-wiki.md\":\"CDYZIBFN\",\"templates_demo.md\":\"BeQX9V3H\",\"templates_grokbot-agents.md\":\"c1s6Flp9\",\"templates_pr-autofixer.md\":\"Bds_XWcV\",\"templates_security-help.md\":\"C3Ny_Qr2\",\"templates_security-reviewer.md\":\"lshxbCLK\",\"templates_triage.md\":\"Co4UNzkZ\",\"troubleshooting.md\":\"CYEAO9bM\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"Agent SDK\",\"description\":\"Filesystem-first framework for building and serving Cursor agents.\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"sdkVersion\":\"0.1.108\",\"nav\":[{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Guides\",\"link\":\"/guides/webhooks\"},{\"text\":\"Templates\",\"link\":\"/templates/demo\"},{\"text\":\"Reference\",\"link\":\"/reference/project-layout\"}],\"search\":{\"provider\":\"local\"},\"outline\":{\"level\":[2,3]},\"sidebar\":[{\"text\":\"Getting started\",\"items\":[{\"text\":\"Overview\",\"link\":\"/\"},{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Scaffold an agent with Cursor\",\"link\":\"/scaffolding-agents\"},{\"text\":\"Convert a Cursor Automation\",\"link\":\"/guides/convert-automation\"},{\"text\":\"Concepts\",\"link\":\"/concepts\"}]},{\"text\":\"Templates\",\"items\":[{\"text\":\"Demo agent\",\"link\":\"/templates/demo\"},{\"text\":\"Grok Bot agents\",\"link\":\"/templates/grokbot-agents\"},{\"text\":\"Code wiki\",\"link\":\"/templates/code-wiki\"},{\"text\":\"Living AGENTS.md\",\"link\":\"/templates/agents-md\"},{\"text\":\"Security reviewer\",\"link\":\"/templates/security-reviewer\"},{\"text\":\"Security help\",\"link\":\"/templates/security-help\"},{\"text\":\"Agentic Owners\",\"link\":\"/templates/agentic-owners\"},{\"text\":\"PR autofixer\",\"link\":\"/templates/pr-autofixer\"},{\"text\":\"Triage agent\",\"link\":\"/templates/triage\"}]},{\"text\":\"Improving agents\",\"items\":[{\"text\":\"Building agents with agents\",\"link\":\"/building-with-agents\"},{\"text\":\"Evals\",\"link\":\"/evals\"},{\"text\":\"Live A/B metrics\",\"link\":\"/ab\"},{\"text\":\"Storage\",\"link\":\"/storage\"},{\"text\":\"Hillclimbing\",\"link\":\"/hillclimbing\"}]},{\"text\":\"Coding-agent skills\",\"collapsed\":true,\"items\":[{\"text\":\"Overview\",\"link\":\"/skills/\"},{\"text\":\"ab\",\"link\":\"/skills/ab\"},{\"text\":\"create-agent\",\"link\":\"/skills/create-agent\"},{\"text\":\"debug\",\"link\":\"/skills/debug\"},{\"text\":\"evals\",\"link\":\"/skills/evals\"},{\"text\":\"framework-map\",\"link\":\"/skills/framework-map\"},{\"text\":\"github\",\"link\":\"/skills/github\"},{\"text\":\"hillclimb\",\"link\":\"/skills/hillclimb\"},{\"text\":\"mcp-auth\",\"link\":\"/skills/mcp-auth\"},{\"text\":\"otel\",\"link\":\"/skills/otel\"},{\"text\":\"setup-slack\",\"link\":\"/skills/setup-slack\"}]},{\"text\":\"Guides\",\"items\":[{\"text\":\"Webhooks & custom channels\",\"link\":\"/guides/webhooks\"},{\"text\":\"GitHub\",\"link\":\"/guides/github\"},{\"text\":\"Slack\",\"link\":\"/guides/slack\"},{\"text\":\"Human-in-the-loop approvals\",\"link\":\"/guides/human-in-the-loop\"},{\"text\":\"Agent-to-agent\",\"link\":\"/guides/agent-to-agent\"},{\"text\":\"Host MCP OAuth\",\"link\":\"/guides/mcp-oauth\"},{\"text\":\"Cursor cloud agents\",\"link\":\"/guides/cloud-agents\"},{\"text\":\"Cursor Grok Bot agents\",\"link\":\"/guides/grokbot-agents\"},{\"text\":\"Self-improvement\",\"link\":\"/guides/improve\"},{\"text\":\"OpenTelemetry\",\"link\":\"/guides/opentelemetry\"}]},{\"text\":\"Operating\",\"items\":[{\"text\":\"Deployment\",\"link\":\"/deployment\"},{\"text\":\"Fix common problems\",\"link\":\"/troubleshooting\"}]},{\"text\":\"Reference\",\"collapsed\":false,\"items\":[{\"text\":\"Project layout\",\"link\":\"/reference/project-layout\"},{\"text\":\"Agent config\",\"link\":\"/reference/agent-config\"},{\"text\":\"Instructions\",\"link\":\"/reference/instructions\"},{\"text\":\"Tools\",\"link\":\"/reference/tools\"},{\"text\":\"prompt\",\"link\":\"/reference/prompt\"},{\"text\":\"Skills\",\"link\":\"/reference/skills\"},{\"text\":\"MCP Connections\",\"link\":\"/reference/connections\"},{\"text\":\"Subagents\",\"link\":\"/reference/subagents\"},{\"text\":\"Extensions\",\"link\":\"/reference/extensions\"},{\"text\":\"Channels\",\"link\":\"/reference/channels\"},{\"text\":\"Schedules & reminders\",\"link\":\"/reference/schedules\"},{\"text\":\"Hooks\",\"link\":\"/reference/hooks\"},{\"text\":\"Artifacts\",\"link\":\"/reference/artifacts\"},{\"text\":\"Turn result\",\"link\":\"/reference/result\"},{\"text\":\"Sessions & streaming\",\"link\":\"/reference/sessions\"},{\"text\":\"Playground\",\"link\":\"/reference/playground\"},{\"text\":\"CLI\",\"link\":\"/reference/cli\"},{\"text\":\"HTTP API\",\"link\":\"/reference/http-api\"}]}]},\"locales\":{},\"scrollOffset\":134,\"cleanUrls\":false}");</script>
|
|
78
|
-
|
|
79
|
-
</body>
|
|
80
|
-
</html>
|
package/dist/docs/ab.md
DELETED
|
@@ -1,332 +0,0 @@
|
|
|
1
|
-
# Live A/B metrics
|
|
2
|
-
|
|
3
|
-
Use `defineAB` to compare variants on live agent sessions. New sessions
|
|
4
|
-
receive a sticky assignment in each enrolled experiment. The Agent SDK folds
|
|
5
|
-
their durable event streams into tool, token, failure, and wall-time
|
|
6
|
-
metrics. You can send cumulative samples to your metrics backend and
|
|
7
|
-
inspect aggregates in the playground.
|
|
8
|
-
|
|
9
|
-
`defineAB` compares live variants through sticky assignment,
|
|
10
|
-
instruction overlays, optional tool branches, and cumulative metrics.
|
|
11
|
-
Metric callbacks observe the result without approving, rejecting, or
|
|
12
|
-
failing a turn. Use [evals](/docs/evals.md) for pass/fail regression checks
|
|
13
|
-
on fixed inputs.
|
|
14
|
-
|
|
15
|
-
## Choose live A/B metrics or evals
|
|
16
|
-
|
|
17
|
-
Both features read the session event stream, but they answer different
|
|
18
|
-
questions.
|
|
19
|
-
|
|
20
|
-
| | Live A/B metrics | Evals |
|
|
21
|
-
| --- | --- | --- |
|
|
22
|
-
| Question | How do variants compare on live sessions? | Does the agent still meet a fixed contract? |
|
|
23
|
-
| Location | `agent/ab.ts` or `agent/ab/<name>.ts` | `evals/**/*.eval.ts` |
|
|
24
|
-
| Input | Dev or production traffic | Frozen prompts and fixtures |
|
|
25
|
-
| Output | Cumulative metrics by session and arm | Pass/fail assertions |
|
|
26
|
-
| How it runs | Automatically on new live sessions | `agent-sdk eval` |
|
|
27
|
-
|
|
28
|
-
There is no `agent-sdk ab` command or assertion API.
|
|
29
|
-
|
|
30
|
-
## Define an experiment
|
|
31
|
-
|
|
32
|
-
Author one experiment in `agent/ab.ts`, add more under
|
|
33
|
-
`agent/ab/<name>.ts`, or use both forms. Each file defines one
|
|
34
|
-
experiment. The experiment name comes from `name` when set. Otherwise,
|
|
35
|
-
the Agent SDK uses `ab` for `agent/ab.ts` and the file stem for files under
|
|
36
|
-
`agent/ab/`.
|
|
37
|
-
|
|
38
|
-
```ts
|
|
39
|
-
// agent/ab/concise-weather.ts
|
|
40
|
-
import {
|
|
41
|
-
defineAB,
|
|
42
|
-
splitBySessionHash,
|
|
43
|
-
} from "@cursor/july/ab";
|
|
44
|
-
|
|
45
|
-
export default defineAB({
|
|
46
|
-
name: "concise-weather",
|
|
47
|
-
variants: {
|
|
48
|
-
control: {
|
|
49
|
-
label: "Baseline",
|
|
50
|
-
},
|
|
51
|
-
treatment: {
|
|
52
|
-
label: "Short replies",
|
|
53
|
-
description: "Adds a one-paragraph response limit.",
|
|
54
|
-
instructions: "Keep weather replies to one short paragraph.",
|
|
55
|
-
},
|
|
56
|
-
},
|
|
57
|
-
split: splitBySessionHash({
|
|
58
|
-
weights: { control: 1, treatment: 1 },
|
|
59
|
-
holdout: 0.1,
|
|
60
|
-
}),
|
|
61
|
-
derive: {
|
|
62
|
-
weatherCalls: (event) =>
|
|
63
|
-
event.type === "action.result" &&
|
|
64
|
-
event.data.toolName === "get_weather"
|
|
65
|
-
? 1
|
|
66
|
-
: null,
|
|
67
|
-
},
|
|
68
|
-
onSample(sample) {
|
|
69
|
-
console.log(
|
|
70
|
-
sample.experiment,
|
|
71
|
-
sample.variant,
|
|
72
|
-
sample.metrics.toolCalls,
|
|
73
|
-
sample.metrics.wallTimeMs
|
|
74
|
-
);
|
|
75
|
-
},
|
|
76
|
-
});
|
|
77
|
-
```
|
|
78
|
-
|
|
79
|
-
Every definition needs:
|
|
80
|
-
|
|
81
|
-
- At least two variants. Variant keys cannot be empty or contain `/` or
|
|
82
|
-
`\`.
|
|
83
|
-
- A `split` function that returns a variant key or `null`.
|
|
84
|
-
- An `onSample` callback for completed or failed turns.
|
|
85
|
-
|
|
86
|
-
`label` and `description` appear with the arm in result surfaces.
|
|
87
|
-
`instructions` changes the prompt for sessions in that arm. `derive`
|
|
88
|
-
adds custom counters.
|
|
89
|
-
|
|
90
|
-
Duplicate experiment names are validation errors. Check discovery
|
|
91
|
-
before you serve:
|
|
92
|
-
|
|
93
|
-
```bash
|
|
94
|
-
agent-sdk validate --dir .
|
|
95
|
-
agent-sdk info --dir . --json
|
|
96
|
-
```
|
|
97
|
-
|
|
98
|
-
The `abs` field in `info` lists the discovered experiment names.
|
|
99
|
-
|
|
100
|
-
## Assign sticky variants
|
|
101
|
-
|
|
102
|
-
Enrollment happens once, when a live session is created and before its
|
|
103
|
-
first turn:
|
|
104
|
-
|
|
105
|
-
1. The Agent SDK records `session.started`.
|
|
106
|
-
2. Each experiment runs its `split` function.
|
|
107
|
-
3. The Agent SDK records one durable `ab.assigned` event per experiment.
|
|
108
|
-
4. The selected arms become available on `session.abs`.
|
|
109
|
-
5. Variant instruction overlays reach the first model turn.
|
|
110
|
-
|
|
111
|
-
A split can return a variant key or `null`. A null assignment is a
|
|
112
|
-
sticky skip for that experiment. It increments the experiment's
|
|
113
|
-
`skipped` total, still appears in the snapshot's `sessions` list with
|
|
114
|
-
`variant: null`, and does not collect arm metrics or call `onSample`.
|
|
115
|
-
|
|
116
|
-
Use the split helper that matches your rollout:
|
|
117
|
-
|
|
118
|
-
| Helper | Behavior |
|
|
119
|
-
| --- | --- |
|
|
120
|
-
| `splitBySessionHash({ weights?, holdout?, salt? })` | Hashes the session id into a reproducible arm; the recommended default |
|
|
121
|
-
| `splitByRandom({ weights?, holdout? })` | Draws once when the session starts, then persists the result |
|
|
122
|
-
| `splitAlways("control")` | Pins every new session to one arm |
|
|
123
|
-
| `splitNone()` | Skips every new session without deleting the experiment |
|
|
124
|
-
| `splitIf(predicate, inner)` | Runs `inner` only when the predicate passes |
|
|
125
|
-
| Custom `split(ctx)` | Returns a declared variant key or `null` |
|
|
126
|
-
|
|
127
|
-
The split context includes the agent name, channel id, session info,
|
|
128
|
-
experiment name, and declared variant keys. For example, enroll only
|
|
129
|
-
Slack sessions:
|
|
130
|
-
|
|
131
|
-
```ts
|
|
132
|
-
split: splitIf(
|
|
133
|
-
(ctx) => ctx.channel.id === "slack",
|
|
134
|
-
splitBySessionHash()
|
|
135
|
-
),
|
|
136
|
-
```
|
|
137
|
-
|
|
138
|
-
Weights default to equal. Non-positive weights leave an arm out of the
|
|
139
|
-
draw, and at least one arm must have a positive weight. `holdout` is the
|
|
140
|
-
fraction of sessions assigned `null`, from `0` through `1`. Change
|
|
141
|
-
`salt` to reshuffle future hash assignments without renaming the
|
|
142
|
-
experiment.
|
|
143
|
-
|
|
144
|
-
If a custom split throws or returns an unknown variant, the Agent SDK logs
|
|
145
|
-
the error and records `variant: null`. The failed decision becomes a
|
|
146
|
-
sticky skip instead of breaking the session.
|
|
147
|
-
|
|
148
|
-
Enrollment only applies to new sessions. Adding an experiment does not
|
|
149
|
-
assign existing conversations. Follow-ups keep the session's original
|
|
150
|
-
arms. Keep experiment names and variant keys stable while you collect
|
|
151
|
-
and compare results.
|
|
152
|
-
|
|
153
|
-
## Change behavior by variant
|
|
154
|
-
|
|
155
|
-
Variant instructions are appended to the agent's base instructions.
|
|
156
|
-
Local sessions receive the merged instructions in `AGENTS.md` before
|
|
157
|
-
every turn. Cloud sessions receive them in the first-turn preamble
|
|
158
|
-
only. For cloud follow-ups, branch through `session.abs` when the arm
|
|
159
|
-
must remain visible to deterministic behavior.
|
|
160
|
-
|
|
161
|
-
Tools can branch on the assignment through `ctx.session.abs`. Hooks can
|
|
162
|
-
read the same field for logging or export:
|
|
163
|
-
|
|
164
|
-
```ts
|
|
165
|
-
const treatment =
|
|
166
|
-
ctx.session.abs?.["concise-weather"] === "treatment";
|
|
167
|
-
|
|
168
|
-
if (treatment) {
|
|
169
|
-
return conciseWeatherResult;
|
|
170
|
-
}
|
|
171
|
-
|
|
172
|
-
return baselineWeatherResult;
|
|
173
|
-
```
|
|
174
|
-
|
|
175
|
-
This makes the assignment available to deterministic code as well as
|
|
176
|
-
the model prompt. Use both patterns together when one experiment must
|
|
177
|
-
steer the prompt and host code at once.
|
|
178
|
-
|
|
179
|
-
`defineAB` does not select a different model or runtime for each arm.
|
|
180
|
-
Keep those settings in `agent/agent.ts`, or write explicit host logic
|
|
181
|
-
when your experiment needs another behavior lever.
|
|
182
|
-
|
|
183
|
-
The split and selected arm can affect agent behavior. `derive` and
|
|
184
|
-
`onSample` only observe the resulting event stream. Errors in either
|
|
185
|
-
callback are logged and never fail the turn.
|
|
186
|
-
|
|
187
|
-
## Collect built-in and custom metrics
|
|
188
|
-
|
|
189
|
-
Metrics accumulate for each session and experiment. When one session
|
|
190
|
-
joins several experiments, every enrolled experiment folds the same
|
|
191
|
-
turn and tool events into its own counters.
|
|
192
|
-
|
|
193
|
-
| Metric | How the Agent SDK calculates it |
|
|
194
|
-
| --- | --- |
|
|
195
|
-
| `turns` | Adds one on `turn.completed` or `turn.failed` |
|
|
196
|
-
| `turnFailures` | Adds one on `turn.failed` |
|
|
197
|
-
| `toolCalls` | Adds one for each `action.result` |
|
|
198
|
-
| `toolErrors` | Adds one when `action.result.data.isError` is true |
|
|
199
|
-
| `inputTokens`, `outputTokens` | Adds usage from completed turns |
|
|
200
|
-
| `cacheReadTokens`, `cacheWriteTokens` | Adds cache usage from completed turns |
|
|
201
|
-
| `costUsd` | Sums the estimated turn cost recorded on `turn.completed` (turns whose model has no known rates contribute 0) |
|
|
202
|
-
| `wallTimeMs` | Sums the time from `turn.started` to its completed or failed event |
|
|
203
|
-
| `custom` | Sums finite numeric deltas returned by `derive` |
|
|
204
|
-
|
|
205
|
-
`onSample` fires after every `turn.completed` and `turn.failed` event
|
|
206
|
-
for an enrolled arm. The sample contains:
|
|
207
|
-
|
|
208
|
-
| Field | Value |
|
|
209
|
-
| --- | --- |
|
|
210
|
-
| `experiment` | Experiment name |
|
|
211
|
-
| `variant`, `variantLabel?` | Sticky arm and optional display label |
|
|
212
|
-
| `sessionId`, `channelId` | Source session |
|
|
213
|
-
| `metrics` | Cumulative metrics through this turn |
|
|
214
|
-
| `reason` | `turn.completed` or `turn.failed` |
|
|
215
|
-
| `at` | Terminal event timestamp |
|
|
216
|
-
|
|
217
|
-
The metrics are cumulative, not per-turn deltas. A second sample from
|
|
218
|
-
the same session includes the first turn's counts.
|
|
219
|
-
|
|
220
|
-
Each `derive` extractor runs on every session event for its enrolled
|
|
221
|
-
experiment, including streamed `message.appended` events. Keep it
|
|
222
|
-
synchronous and cheap. Return a finite number to add a delta, or
|
|
223
|
-
`null` to skip the event. Send samples to your metrics service from
|
|
224
|
-
`onSample`; do not perform network or disk work in `derive`.
|
|
225
|
-
|
|
226
|
-
Skipped sessions never call `onSample`. Errors from `derive` or
|
|
227
|
-
`onSample` are logged, then metric collection continues.
|
|
228
|
-
|
|
229
|
-
## Inspect assignments and results
|
|
230
|
-
|
|
231
|
-
Open the playground's **A/Bs** tab to see aggregate arm totals and
|
|
232
|
-
per-session assignments. The tab reads `GET /v1/abs`.
|
|
233
|
-
|
|
234
|
-
The response has two views of the same durable data:
|
|
235
|
-
|
|
236
|
-
| Field | Contents |
|
|
237
|
-
| --- | --- |
|
|
238
|
-
| `experiments` | Declared variants, skipped-session count, arm session counts, and aggregate metrics |
|
|
239
|
-
| `sessions` | Visible sessions with their assignments and cumulative metrics |
|
|
240
|
-
|
|
241
|
-
`GET /v1/abs` returns sessions visible to the current principal by
|
|
242
|
-
default. In `--dev`, loopback requests include every session. Add
|
|
243
|
-
`--allow-anonymous` to include every session from non-loopback callers
|
|
244
|
-
too.
|
|
245
|
-
|
|
246
|
-
The session event stream is the source of truth for assignment + fold.
|
|
247
|
-
`GET /v1/abs` recomputes aggregates from those logs. Any
|
|
248
|
-
`agent/storage.ts` exports samples and snapshots durably: an authored
|
|
249
|
-
`abs` table when the backend has a native shape for it, or the table
|
|
250
|
-
derived over the KV core otherwise. See
|
|
251
|
-
[Storage](/docs/storage.md#eval-and-a-b-tables).
|
|
252
|
-
|
|
253
|
-
## Configure the playground fold window
|
|
254
|
-
|
|
255
|
-
Assignments and foldable metrics already persist in each session's
|
|
256
|
-
event stream. The optional `agent/ab.config.ts` only caps how many
|
|
257
|
-
sessions the playground and `GET /v1/abs` fold:
|
|
258
|
-
|
|
259
|
-
```ts
|
|
260
|
-
import { defineABConfig } from "@cursor/july/ab";
|
|
261
|
-
|
|
262
|
-
export default defineABConfig({
|
|
263
|
-
// Optional. Defaults to 200. Only affects GET /v1/abs / A/Bs tab.
|
|
264
|
-
maxPlaygroundSessions: 500,
|
|
265
|
-
});
|
|
266
|
-
```
|
|
267
|
-
|
|
268
|
-
`maxPlaygroundSessions` keeps the newest sessions in the fold. It does
|
|
269
|
-
not prune session logs or change assignment. For export to S3, a DB, or
|
|
270
|
-
your metrics vendor, send samples from `onSample` or declare a storage
|
|
271
|
-
`abs` table.
|
|
272
|
-
|
|
273
|
-
## Keep assignments durable
|
|
274
|
-
|
|
275
|
-
The append-only event stream is the source of truth. Each
|
|
276
|
-
`ab.assigned` event persists a variant key or null skip. Built-in
|
|
277
|
-
metrics come from the turn and tool events that follow it.
|
|
278
|
-
|
|
279
|
-
After a server restart or a parked session resumes, the live collector
|
|
280
|
-
replays the stream to rebuild cumulative counters. Replay does not call
|
|
281
|
-
`onSample` (or write to the storage `abs` table) for historical turns.
|
|
282
|
-
Only a new completed or failed turn emits another sample.
|
|
283
|
-
|
|
284
|
-
The snapshot API also replays `derive` across the full stream, so
|
|
285
|
-
custom totals match the current extractor. Changing a derive function
|
|
286
|
-
can change historical snapshot totals. Treat metric definitions as
|
|
287
|
-
versioned experiment code.
|
|
288
|
-
|
|
289
|
-
## Keep eval traffic separate
|
|
290
|
-
|
|
291
|
-
Sessions created by `agent-sdk eval` and the playground Evals runner use
|
|
292
|
-
`purpose: "eval"`. They skip A/B enrollment entirely:
|
|
293
|
-
|
|
294
|
-
- No split function runs.
|
|
295
|
-
- No `ab.assigned` event is recorded.
|
|
296
|
-
- No `onSample` callback fires.
|
|
297
|
-
- The session is omitted from `GET /v1/abs`.
|
|
298
|
-
|
|
299
|
-
Ordinary chat, `agent-sdk run`, Slack, GitHub, and other channel sessions
|
|
300
|
-
use the live purpose. You do not need `splitIf` to exclude eval traffic.
|
|
301
|
-
|
|
302
|
-
## Know the boundaries
|
|
303
|
-
|
|
304
|
-
`defineAB` provides sticky assignment, variant instructions,
|
|
305
|
-
`session.abs` for tools, cumulative metrics, and local inspection. It
|
|
306
|
-
does not provide:
|
|
307
|
-
|
|
308
|
-
- A test command, assertion API, or pass/fail result
|
|
309
|
-
- Statistical significance calculations
|
|
310
|
-
- An experiment rollout or lifecycle service
|
|
311
|
-
- Per-variant model or runtime configuration
|
|
312
|
-
- A built-in analytics warehouse (bring your own via `onSample` or the
|
|
313
|
-
storage `abs` table)
|
|
314
|
-
|
|
315
|
-
Use [evals](/docs/evals.md) to protect known behavior. Use `onSample` or a
|
|
316
|
-
storage `abs` table when you need sample/snapshot exports beyond the
|
|
317
|
-
session event log.
|
|
318
|
-
|
|
319
|
-
## What's next
|
|
320
|
-
|
|
321
|
-
Continue with these pages:
|
|
322
|
-
|
|
323
|
-
- [Evals](/docs/evals.md): pass/fail regression checks on fixed inputs
|
|
324
|
-
- [Hillclimbing](/docs/hillclimbing.md): improve an agent against fixed
|
|
325
|
-
fixtures
|
|
326
|
-
- [Hooks](/docs/reference/hooks.md): other event-stream consumers
|
|
327
|
-
- [Sessions and streaming](/docs/reference/sessions.md): the
|
|
328
|
-
`ab.assigned` event and durable log
|
|
329
|
-
- [Playground](/docs/reference/playground.md): the A/Bs tab
|
|
330
|
-
- [HTTP API](/docs/reference/http-api.md): `GET /v1/abs`
|
|
331
|
-
- [Live A/B metrics skill](/docs/skills/ab.md): have a coding agent
|
|
332
|
-
wire an experiment
|